Research article

Multi-phase features interaction transformer network for liver tumor segmentation and microvascular invasion assessment in contrast-enhanced CT

  • † These two authors contributed equally
  • Received: 13 January 2024 Revised: 03 March 2024 Accepted: 05 March 2024 Published: 24 April 2024
  • Precise segmentation of liver tumors from computed tomography (CT) scans is a prerequisite step in various clinical applications. Multi-phase CT imaging enhances tumor characterization, thereby assisting radiologists in accurate identification. However, existing automatic liver tumor segmentation models did not fully exploit multi-phase information and lacked the capability to capture global information. In this study, we developed a pioneering multi-phase feature interaction Transformer network (MI-TransSeg) for accurate liver tumor segmentation and a subsequent microvascular invasion (MVI) assessment in contrast-enhanced CT images. In the proposed network, an efficient multi-phase features interaction module was introduced to enable bi-directional feature interaction among multiple phases, thus maximally exploiting the available multi-phase information. To enhance the model's capability to extract global information, a hierarchical transformer-based encoder and decoder architecture was designed. Importantly, we devised a multi-resolution scales feature aggregation strategy (MSFA) to optimize the parameters and performance of the proposed model. Subsequent to segmentation, the liver tumor masks generated by MI-TransSeg were applied to extract radiomic features for the clinical applications of the MVI assessment. With Institutional Review Board (IRB) approval, a clinical multi-phase contrast-enhanced CT abdominal dataset was collected that included 164 patients with liver tumors. The experimental results demonstrated that the proposed MI-TransSeg was superior to various state-of-the-art methods. Additionally, we found that the tumor mask predicted by our method showed promising potential in the assessment of microvascular invasion. In conclusion, MI-TransSeg presents an innovative paradigm for the segmentation of complex liver tumors, thus underscoring the significance of multi-phase CT data exploitation. The proposed MI-TransSeg network has the potential to assist radiologists in diagnosing liver tumors and assessing microvascular invasion.

    Citation: Wencong Zhang, Yuxi Tao, Zhanyao Huang, Yue Li, Yingjia Chen, Tengfei Song, Xiangyuan Ma, Yaqin Zhang. Multi-phase features interaction transformer network for liver tumor segmentation and microvascular invasion assessment in contrast-enhanced CT[J]. Mathematical Biosciences and Engineering, 2024, 21(4): 5735-5761. doi: 10.3934/mbe.2024253

    Related Papers:

    [1] Yanlin Li, Yuquan Xie, Manish Kumar Gupta, Suman Sharma . On projective Ricci curvature of cubic metrics. AIMS Mathematics, 2025, 10(5): 11305-11315. doi: 10.3934/math.2025513
    [2] Salah G. Elgendi . Parallel one forms on special Finsler manifolds. AIMS Mathematics, 2024, 9(12): 34356-34371. doi: 10.3934/math.20241636
    [3] Fangmin Dong, Benling Li . On a class of weakly Landsberg metrics composed by a Riemannian metric and a conformal 1-form. AIMS Mathematics, 2023, 8(11): 27328-27346. doi: 10.3934/math.20231398
    [4] Yanlin Li, Aydin Gezer, Erkan Karakaş . Some notes on the tangent bundle with a Ricci quarter-symmetric metric connection. AIMS Mathematics, 2023, 8(8): 17335-17353. doi: 10.3934/math.2023886
    [5] Rattanasak Hama, Sorin V. Sabau . Randers metrics on two-spheres of revolution with simple cut locus. AIMS Mathematics, 2023, 8(11): 26213-26236. doi: 10.3934/math.20231337
    [6] Yayun Chen, Tongzhu Li . Classification of spacelike conformal Einstein hypersurfaces in Lorentzian space Rn+11. AIMS Mathematics, 2023, 8(10): 23247-23271. doi: 10.3934/math.20231182
    [7] Cagri Karaman . Statistical connections on decomposable Riemann manifold. AIMS Mathematics, 2020, 5(5): 4722-4733. doi: 10.3934/math.2020302
    [8] Derya Sağlam, Cumali Sunar . Translation hypersurfaces of semi-Euclidean spaces with constant scalar curvature. AIMS Mathematics, 2023, 8(2): 5036-5048. doi: 10.3934/math.2023252
    [9] Rabia Cakan Akpınar, Esen Kemer Kansu . Metallic deformation on para-Sasaki-like para-Norden manifold. AIMS Mathematics, 2024, 9(7): 19125-19136. doi: 10.3934/math.2024932
    [10] Salah G. Elgendi, Zoltán Muzsnay . The geometry of geodesic invariant functions and applications to Landsberg surfaces. AIMS Mathematics, 2024, 9(9): 23617-23631. doi: 10.3934/math.20241148
  • Precise segmentation of liver tumors from computed tomography (CT) scans is a prerequisite step in various clinical applications. Multi-phase CT imaging enhances tumor characterization, thereby assisting radiologists in accurate identification. However, existing automatic liver tumor segmentation models did not fully exploit multi-phase information and lacked the capability to capture global information. In this study, we developed a pioneering multi-phase feature interaction Transformer network (MI-TransSeg) for accurate liver tumor segmentation and a subsequent microvascular invasion (MVI) assessment in contrast-enhanced CT images. In the proposed network, an efficient multi-phase features interaction module was introduced to enable bi-directional feature interaction among multiple phases, thus maximally exploiting the available multi-phase information. To enhance the model's capability to extract global information, a hierarchical transformer-based encoder and decoder architecture was designed. Importantly, we devised a multi-resolution scales feature aggregation strategy (MSFA) to optimize the parameters and performance of the proposed model. Subsequent to segmentation, the liver tumor masks generated by MI-TransSeg were applied to extract radiomic features for the clinical applications of the MVI assessment. With Institutional Review Board (IRB) approval, a clinical multi-phase contrast-enhanced CT abdominal dataset was collected that included 164 patients with liver tumors. The experimental results demonstrated that the proposed MI-TransSeg was superior to various state-of-the-art methods. Additionally, we found that the tumor mask predicted by our method showed promising potential in the assessment of microvascular invasion. In conclusion, MI-TransSeg presents an innovative paradigm for the segmentation of complex liver tumors, thus underscoring the significance of multi-phase CT data exploitation. The proposed MI-TransSeg network has the potential to assist radiologists in diagnosing liver tumors and assessing microvascular invasion.



    The Ricci curvature in Finsler geometry naturally generalizes the Ricci curvature in Riemannian geometry. However, in Finsler geometry, there are several versions of the definition of scalar curvature because the Ricci curvature tensor is defined in different forms. Here we adopt the definition of scalar curvature, which was introduced by Akbar–Zadeh [1,see (2.1)]. Tayebi [11] characterized general fourth-root metrics with isotropic scalar curvature. Moreover, he studied Bryant metrics with isotropic scalar curvature. Later, a locally conformally flat (α,β)-metric with weakly isotropic scalar curvature was studied by Chen–Xia [4]. They proved that its scalar curvature must vanish. Recently, Cheng–Gong [5] proved that if a Randers metric is of weakly isotropic scalar curvature, then it must be of isotropic S-curvature. Furthermore, they concluded that when a locally conformally flat Randers metric is of weakly isotropic scalar curvature, it is Minkowskian or Riemannian. Very recently, Ma–Zhang–Zhang [8] showed that the Kropina metric with isotropic scalar curvature is equivalent to an Einstein Kropina metric according to the navigation data.

    Shimada [9] first developed the theory of m-th root metrics as an interesting example of Finsler metrics, immediately following Matsumoto and Numata's theory of cubic metrics [7]. It is applied to biology as an ecological metric by Antonelli [2]. Later, many scholars studied these metrics ([3,6,10,11,12], etc). In [13], cubic Finsler manifolds in dimensions two or three were studied by Wegener. He only abstracted his PhD thesis and barely did all the calculations in that paper. Kim and Park [6] studied the m-th root Finsler metrics which admit (α,β)types. In [12], Tayebi–Razgordani–Najafi showed that if the locally conformally flat cubic metric is of relatively isotropic mean Landsberg curvature on a manifold M of dimension n(3), then it is a Riemannian metric or a locally Minkowski metric. Tripathia–Khanb–Chaubey [10] considered a cubic (α,β)-metric which is a special class of p-power Finsler metric, and obtained the conditions under which the Finsler space with such special metric will be projectively flat. Further, they obtained in which case this Finsler space will be a Berwald space or Douglas space.

    In this paper, we mainly focus on m-th root metrics with weakly isotropic scalar curvature and obtain the following results:

    Theorem 1.1. Let the m(3)-th root metric F be of weakly isotropic scalar curvature. Then its scalar curvature must vanish.

    Let A:=ai1i2im(x)yi1yi2yim. If A=Fm is irreducible, then the further result is obtained as follows:

    Theorem 1.2. Let F=mA be the m(3)-th root metric. Assume that A is irreducible. Then the following are equivalent: (i) F is of weakly isotropic scalar curvature; (ii) its scalar curvature vanishes; (iii) it is Ricci-flat.

    Based on Theorem 1.1, we obtain the result for locally conformally flat cubic Finsler metrics as following:

    Theorem 1.3. Let F be a locally conformally flat cubic Finsler metric on a manifold M of dimension n(3). If F is of weakly isotropic scalar curvature, then F must be locally Minkowskian.

    In this section, we mainly introduce several geometric quantities in Finsler geometry and several results that will be used later.

    Let M be an n(3)-dimensional smooth manifold. The points in the tangent bundle TM are denoted by (x,y), where xM and yTxM. Let (xi,yi) be the local coordinates of TM with y=yixi. A Finsler metric on M is a function F:TM[0,+) such that

    (1) F is smooth in TM{0};

    (2) F(x,λy)=λF(x,y) for any λ>0;

    (3) The fundamental quadratic form g=gij(x,y)dxidxj, where

    gij(x,y)=[12F2(x,y)]yiyj

    is positively definite. We use the notations: Fyi:=Fyi, Fxi:=Fxi,F2yiyj:=2F2yiyj.

    Let F be a Finsler metric on an n-dimensional manifold M, and let Gi be the geodesic coefficients of F, which are defined by

    Gi:=14gij(F2xkyjykF2xj),

    where (gij)=(gij)1. For any xM and yTxM{0}, the Riemann curvature Ry:=Rik(x,y)xidxk is defined by

    Rik:=2GixkGixjykyj+2GjGiyjykGiyjGjyk.

    The Ricci curvature Ric is the trace of the Riemann curvature defined by

    Ric:=Rkk.

    The Ricci tensor is

    Ricij:=12Ricyiyj.

    By the homogeneity of Ric, we have Ric=Ricijyiyj. The scalar curvature r of F is defined as

    r:=gijRicij. (2.1)

    A Finsler metric is said to be of weakly isotropic scalar curvature if there exists a 1-form θ=θi(x)yi and a scalar function χ=χ(x) such that

    r=n(n1)(θF+χ). (2.2)

    An (α,β)-metric is a Finsler metric of the form

    F=αϕ(s),

    where α=aij(x)yiyj is a Riemannian metric, β=bi(x)yi is a 1-form, s:=βα and b:=∥βα<b0. It has been proved that F=αϕ(s) is a positive definite Finsler metric if and only if ϕ=ϕ(s) is a positive C function on (b0,b0) satisfying the following condition:

    ϕ(s)sϕ(s)+(Bs2)ϕ(s)>0,|s|b<b0, (2.3)

    where B:=b2.

    Let F=3aijk(x)yiyjyk be a cubic metric on a manifold M of dimension n3. By choosing a suitable non-degenerate quadratic form α=aij(x)yiyj and one-form β=bi(x)yi, it can be written in the form

    F=3pβα2+qβ3,

    where p and q are real constants such that p+qB0 (see [6]). The above equation can be rewritten as

    F=α(ps+qs3)13,

    which means that F is also an (α,β)-metric with ϕ(s)=(ps+qs3)13. Then, by (2.3), we obtain

    p2B+p(4p+3qB)s2>0. (2.4)

    Two Finsler metrics F and ˜F on a manifold M are said to be conformally related if there is a scalar function κ=κ(x) on M such that F=eκ(x)˜F. Particularly, an (α,β)-metric F=αϕ(βα) is said to be conformally related to a Finsler metric ˜F if F=eκ(x)˜F with ˜F=˜αϕ(˜s)=˜αϕ(˜β˜α). In the following, we always use symbols with a tilde to denote the corresponding quantities of the metric ˜F. Note that α=eκ(x)˜α, β=eκ(x)˜β, thus ˜s=s.

    A Finsler metric that is conformally related to a locally Minkowski metric is said to be locally conformally flat. Thus, a locally conformally flat (α,β)-metric F has the form F=eκ(x)˜F, where ˜F=˜αϕ(˜β˜α) is a locally Minkowski metric.

    Denoting

    rij:=12(bi|j+bj|i),sij:=12(bi|jbj|i),rij:=ailrlj,sij:=ailslj,rj:=birij,r:=biri,sj:=bisij,r00:=rijyiyj,si0:=sijyj,s0:=siyi,

    where bi:=aijbj, bi|j denotes the covariant differentiation with respect to α.

    Let Gi and Giα denote the geodesic coefficients of F and α, respectively. The geodesic coefficients Gi of F=αϕ(βα) are related to Giα by

    Gi=Giα+αQsi0+(2Qαs0+r00)(Ψbi+Θα1yi),

    where

    Q:=ϕϕsϕ,Θ:=ϕϕs(ϕϕ+ϕϕ)2ϕ[(ϕsϕ)+(Bs2)ϕ],Ψ:=ϕ2[(ϕsϕ)+(Bs2)ϕ].

    Assume that F=αϕ(βα) is conformally related to a Finsler metric ˜F=˜αϕ(˜β˜α) on M, i.e., F=eκ(x)˜F. Then

    aij=e2κ(x)˜aij,bi=eκ(x)˜bi,˜b:=∥˜β˜α=˜aij˜bi˜bj=b.

    Further, we have

    bi|j=eκ(x)(˜bij˜bjκi+˜blκl˜aij),αΓlij=˜α˜Γlij+κjδli+κiδljκl˜aij,rij=eκ(x)˜rij+12eκ(x)(˜bjκi˜biκj+2˜blκl˜aij),sij=eκ(x)˜sij+12eκ(x)(˜biκj˜bjκi),ri=˜ri+12(˜blκl˜bib2κi),r=eκ(x)˜r,si=˜si+12(b2κi˜blκl˜bi),rii=eκ(x)˜rii+(n1)eκ(x)˜biκi,sji=eκ(x)˜sji+12eκ(x)(˜bjκi˜biκj).

    Here ˜bij denotes the covariant derivatives of ˜bi with respect to ˜α, αΓmij and ˜α˜Γmij denote Levi–Civita connections with respect to α and ˜α, respectively. In the following, we adopt the notations κi:=κ(x)xi, κij:=2κ(x)xixj, κi:=˜aijκj, ˜bi:=˜aij˜bj, f:=˜biκi, f1:=κij˜biyj, f2:=κij˜bi˜bj, κ0:=κiyi, κ00:=κijyiyj and κ2˜α:=˜aijκiκj.

    Lemma 2.1. ([4]) Let F=eκ(x)˜F, where ˜F=˜αϕ(˜β˜α) is locally Minkowskian. Then the Ricci curvature of F is determined by

    Ric=D1κ2˜α˜α+D2κ20+D3κ0f˜α+D4f2˜α2+D5f1˜α+D6˜α2+D7κ00,

    where Dk(k=1,...,7) is listed in Lemma 3.2 in [4].

    Lemma 2.2. ([4]) Let F=eκ(x)˜F, where ˜F=˜αϕ(˜β˜α) is locally Minkowskian. Then the scalar curvature of F is determined by

    r=12e2κ(x)ρ1[Σ1(τ+ηλ2)Σ2λη˜αΣ3η˜α2Σ4],

    where

    τ:=δ1+δB,η:=μ1+Y2μ,λ:=εδs1+δB,δ:=ρ0ε2ρ2ρ,ε:=ρ1ρ2,μ:=ρ2ρ,Y:=AijYiYj,Aij:=aij+δbibj,ρ:=ϕ(ϕsϕ),ρ0:=ϕϕ+ϕϕ,ρ1:=s(ϕϕ+ϕϕ)+ϕϕ,ρ2:=s[s(ϕϕ+ϕϕ)ϕϕ],

    and Σi(i=1,...,4) are listed in the proof of Lemma 3.3 in [4].

    Lemma 2.3. ([14]) Let m-th root metric F=mai1i2im(x)yi1yi2yim be a Finsler metric on a manifold of dimension n. Then the Ricci curvature of F is a rational function in y.

    In this section, we will prove the main theorems. Firstly, we give the proof of Theorem 1.1.

    The proof of Theorem 1.1. For an m-th root metric F=mai1i2im(x)yi1yi2yim on a manifold M, the inverse of the fundamental tensor of F is given by (see [14])

    gij=1(m1)F2(AAij+(m2)yiyj), (3.1)

    where Aij=1m(m1)2Ayiyj and (Aij)=(Aij)1. Thus, F2gij are rational functions in y.

    By Lemma 2.3, the Ricci curvature Ric of m-th root metric is a rational function in y. Thus, Ricij:=Ricyiyj are rational functions. According to (2.1), we have

    F2r=F2gijRicij. (3.2)

    This means that F2r is a rational function in y.

    On the other hand, if F is of weakly isotropic scalar curvature, according to (2.2), we obtain

    F2r=n(n1)(θF+χF2),

    where θ is a 1-form and χ is a scalar function. The right side of the above equation is an irrational function in y. Comparing it with (3.2), we have r=0.

    In the following, the proof of Theorem 1.2 is given.

    The proof of Theorem 1.2. By Theorem 1.1, we conclude that F is of weakly isotropic scalar curvature if and only if its scalar curvature vanishes. So we just need to prove that (ii) is equivalent to (iii). Assume that the scalar curvature vanishes. Hence, by (3.1), 0=r=gijRicij=1m1F2(AAij+(m2)yiyj)Ricij holds. It means that

    0=(AAij+(m2)yiyj)Ricij=AAijRicij+(m2)Ric.

    Since A is irreducible, Ric must be divided by A. Thus, Ric=0.

    Conversely, if Ric=0, then by the definition of r we have r=0.

    Based on Theorem 1.1, we can prove Theorem 1.3 for locally conformally flat cubic metrics.

    The proof of Theorem 1.3. Assume that the locally conformally flat cubic metric F is of weakly isotropic scalar curvature. Then, by Lemma 2.2 and Theorem 1.1, we obtain the scalar curvature vanishes, i.e.,

    Σ1(τ+ηλ2)Σ2λη˜αΣ3η˜α2Σ4=0.

    Further, by detailed expressions of Σi(i=1,4), the above equation can be rewritten as

    B(4p+3qB)κ204(4p+3qB)˜βκ0f+4p˜α2f2(4p+3qB)8˜α2s2γ7+Tγ6=0, (3.3)

    where γ:=pB˜α2(4p+3qB)˜β2 and T has no γ1.

    Thus, the first term of (3.3) can be divided by γ. It means that there is a function h(x) on M such that

    B(4p+3qB)κ204(4p+3qB)˜βκ0f+4p˜α2f2=h(x)γ.

    The above equation can be rewritten as

    B(4p+3qB)κ204(4p+3qB)˜βκ0f+4p˜α2f2=h(x)[pB˜α2(4p+3qB)˜β2]. (3.4)

    Differentiating (3.4) with yi yields

    B(4p+3qB)κ0κi2(4p+3qB)(˜biκ0+˜βκi)f+4p˜ailylf2=h(x)[pB˜ailyl(4p+3qB)˜β˜bi]. (3.5)

    Differentiating (3.5) with yj yields

    B(4p+3qB)κiκj2(4p+3qB)(˜biκj+˜bjκi)f+4p˜aijf2=h(x)[pB˜aij(4p+3qB)˜bi˜bj].

    Contracting the above with ˜bi˜bj yields

    Bf2(8p+9qB)=3B2h(x)(p+qB).

    Thus, we have

    h(x)=(8p+9qB)f23B(p+qB). (3.6)

    Substituting (3.6) into (3.5) and contracting (3.5) with ˜bi yield

    (4p+3qB)f(f˜βBκ0)=0. (3.7)

    Furthermore, by (2.4) and 4p+3qB0, we have f(f˜βBκ0)=0.

    Case I: f=0. It means h(x)=0 by (3.6). Thus, one has that κi=0 by (3.4), which means

    κ=constant.

    Case II: f0. It implies that f˜βBκ0=0. Substituting it into (3.4), we obtain

    ˜β2=B˜α2,

    which does not exist.

    Above all, we have κ=constant. Thus we conclude that the conformal transformation must be homothetic.

    X. Zhang: Conceptualization, Validation, Formal analysis, Resources, Software, Investigation, Methodology, Supervision, Writing-original draft, Writing-review and editing, Project administration, Funding acquisition; C. Ma: Formal analysis, Software, Investigation, Supervision, Writing-review and editing; L. Zhao: Resources, Investigation, Supervision. All authors have read and agreed to the published version of the manuscript.

    The authors declare they have not used Artificial Intelligence (AI) tools in the creation of this article.

    Xiaoling Zhang's research is supported by National Natural Science Foundation of China (No. 11961061, 11761069).

    The authors declare that they have no conflicts of interest.



    [1] H. Sung, J. Ferlay, R. L. Siegel, M. Laversanne, I. Soerjomataram, A. Jemal, et al., Global Cancer Statistics 2020: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries, CA Cancer J. Clin., 71 (2021), 209–249. https://doi.org/10.3322/caac.21660 doi: 10.3322/caac.21660
    [2] J. M. Llovet, R. K. Kelley, A. Villanueva, A. G. Singal, E. Pikarsky, S. Roayaie, et al., Hepatocellular carcinoma, Nat. Rev. Dis. Primers, 7 (2021), 6. https://doi.org/10.1038/s41572-020-00240-3 doi: 10.1038/s41572-020-00240-3
    [3] F. X. Bosch, J. Ribes, M. Díaz, R. Cléries, Primary liver cancer: worldwide incidence and trends, Gastroenterology, 127 (2004), S5–S16. https://doi.org/10.1053/j.gastro.2004.09.011 doi: 10.1053/j.gastro.2004.09.011
    [4] X. Wu, J. Li, C. Wang, G. Zhang, N. Zheng, X. Wang, Application of different imaging methods in the early diagnosis of primary hepatic carcinoma, Gastroenterol. Res. Pract., 2016 (2016), 8763205. https://doi.org/10.1155/2016/8763205 doi: 10.1155/2016/8763205
    [5] K. Song, D. Wu, Shared decision-making in the management of patients with inflammatory bowel disease, World J. Gastroenterol., 28 (2022), 3092–3100. https://doi.org/10.3748%2Fwjg.v28.i26.3092
    [6] C. Chang, H. Chen, Y. Chang, M. Yang, C. Lo, W. Ko, et al., Computer-aided diagnosis of liver tumors on computed tomography images, Comput. Methods Programs Biomed., 145 (2017), 45–51. https://doi.org/10.1016/j.cmpb.2017.04.008 doi: 10.1016/j.cmpb.2017.04.008
    [7] W. Li, F. Jia, Q. Hu, Automatic segmentation of liver tumor in CT images with deep convolutional neural networks, J. Comput. Commun., 3 (2015), 146–151. http://dx.doi.org/10.4236/jcc.2015.311023 doi: 10.4236/jcc.2015.311023
    [8] R. Naseem, Z. A. Khan, N. Satpute, A. Beghdadi, F. A. Cheikh, J. Olivares, Cross-modality guided contrast enhancement for improved liver tumor image segmentation, IEEE Access, 9 (2021), 118154–118167. https://doi.org/10.1109/ACCESS.2021.3107473 doi: 10.1109/ACCESS.2021.3107473
    [9] L. Wang, M. Wu, R. Li, X. Xu, C. Zhu, X. Feng, MVI-Mind: A novel deep-learning strategy using computed tomography (CT)-based radiomics for end-to-end high efficiency prediction of microvascular invasion in hepatocellular carcinoma, Cancers, 14 (2022), 2956. https://doi.org/10.3390/cancers14122956 doi: 10.3390/cancers14122956
    [10] Y. Jiang, S. Cao, S. Cao, J. Chen, G. Wang, W. Shi, et al., Preoperative identification of microvascular invasion in hepatocellular carcinoma by XGBoost and deep learning, J. Cancer Res. Clin. Oncol., 147 (2021), 821–833. https://doi.org/10.1007/s00432-020-03366-9 doi: 10.1007/s00432-020-03366-9
    [11] A. Radtke, S. Nadalin, G. C. Sotiropoulos, E. P. Molmenti, T. Schroeder, C. Valentin-Gamazo, et al., Computer-assisted operative planning in adult living donor liver transplantation: A new way to resolve the dilemma of the middle hepatic vein, World J. Surg., 31 (2007), 175–185. https://doi.org/10.1007/s00268-005-0718-1 doi: 10.1007/s00268-005-0718-1
    [12] P. Liang, Y. Wang, X. Yu, B. Dong, Malignant liver tumors: treatment with percutaneous microwave ablation—complications among cohort of 1136 patients, Radiology, 251 (2009), 933–940. https://doi.org/10.1148/radiol.2513081740 doi: 10.1148/radiol.2513081740
    [13] S. Gul, M. S. Khan, A. Bibi, A. Khandakar, M. A. Ayari, M. E. H. Chowdhury, Deep learning techniques for liver and liver tumor segmentation: A review, Comput. Biol. Med., 147 (2022), 105620. https://doi.org/10.1016/j.compbiomed.2022.105620 doi: 10.1016/j.compbiomed.2022.105620
    [14] L. Soler, H. Delingette, G. Malandain, J. Montagnat, N. Ayache, C. Koehl, et al., Fully automatic anatomical, pathological, and functional segmentation from CT scans for hepatic surgery, Comput. Aided Surg., 6 (2001), 131–142. https://doi.org/10.3109/10929080109145999 doi: 10.3109/10929080109145999
    [15] H. A. Nugroho, D. Ihtatho, H. Nugroho, Contrast enhancement for liver tumor identification, in International Conference on Medical Image Computing and Computer-Assisted Intervention, 41 (2008), 201. https://doi.org/10.54294/1uhwld
    [16] M. Esfandiarkhani, A. H. Foruzan, A generalized active shape model for segmentation of liver in low-contrast CT volumes, Comput. Biol. Med., 82 (2017), 59–70. https://doi.org/10.1016/j.compbiomed.2017.01.009 doi: 10.1016/j.compbiomed.2017.01.009
    [17] D. Wong, J. Liu, F. Yin, Q. Tian, W. Xiong, J. Zhou, et al., A semi-automated method for liver tumor segmentation based on 2D region growing with knowledge-based constraints, in International Conference on Medical Image Computing and Computer-Assisted Intervention, 41 (2008), 159. https://doi.org/10.54294/25etax
    [18] L. Fernandez-de-Manuel, J. L. Rubio, M. J. Ledesma-Carbayo, J. Pascau, J. M. Tellado, E. Ramon, et al., 3D liver segmentation in preoperative CT images using a level-sets active surface method, in International Conference of the IEEE Engineering in Medicine and Biology Society, (2009), 3625–3628. https://doi.org/10.1109/iembs.2009.5333760
    [19] S. S. Kumar, R. S. Moni, J. Rajeesh, An automatic computer-aided diagnosis system for liver tumours on computed tomography images, Comput. Electr. Eng., 39 (2013), 1516–1526. https://doi.org/10.1016/j.compeleceng.2013.02.008 doi: 10.1016/j.compeleceng.2013.02.008
    [20] R. Kaur, L. Kaur, S. Gupta, Enhanced K-mean clustering algorithm for liver image segmentation to extract cyst region, in IJCA Special Issue on Novel Aspects of Digital Imaging Applications, 1 (2011), 59–66.
    [21] T. Zhou, S. Canu, S. Ruan, Fusion based on attention mechanism and context constraint for multi-modal brain tumor segmentation, Comput. Med. Imaging Graphics, 86 (2020), 101811. https://doi.org/10.1016/j.compmedimag.2020.101811 doi: 10.1016/j.compmedimag.2020.101811
    [22] J. Dolz, K. Gopinath, J. Yuan, H. Lombaert, C. Desrosiers, I. B. Ayed, HyperDense-Net: a hyper-densely connected CNN for multi-modal image segmentation, IEEE Trans. Med. Imaging, 38 (2018), 1116–1126. https://doi.org/10.1109/TMI.2018.2878669 doi: 10.1109/TMI.2018.2878669
    [23] Q. Yu, Y. Shi, J. Sun, Y. Gao, J. Zhu, Y. Dai, Crossbar-net: a novel convolutional neural network for kidney tumor segmentation in CT images, IEEE Trans. Image Process., 28 (2019), 4060–4074. https://doi.org/10.1109/TIP.2019.2905537 doi: 10.1109/TIP.2019.2905537
    [24] X. Ma, L. M. Hadjiiski, J. Wei, H. P. Chan, K. H. Cha, R. H. Cohan, et al., U‐Net based deep learning bladder segmentation in CT urography, Med. Phys., 46 (2019), 1752–1765. https://doi.org/10.1002/mp.13438 doi: 10.1002/mp.13438
    [25] P. F. Christ, M. E. A. Elshaer, F. Ettlinger, S. Tatavarty, M. Bickel, P. Bilic, et al., Automatic liver and lesion segmentation in CT using cascaded fully convolutional neural networks and 3D conditional random fields, in International Conference on Medical Image Computing and Computer-Assisted Intervention, (2016), 415–423. https://doi.org/10.1007/978-3-319-46723-8_48
    [26] G. Chlebus, A. Schenk, J. H. Moltz, B. van Ginneken, H. K. Hahn, H. Meine, Automatic liver tumor segmentation in CT with fully convolutional neural networks and object-based postprocessing, Sci. Rep., 8 (2018), 15497. https://doi.org/10.1038/s41598-018-33860-7 doi: 10.1038/s41598-018-33860-7
    [27] O. Ronneberger, P. Fischer, T. Brox, U-net: Convolutional networks for biomedical image segmentation, in International Conference on Medical Image Computing and Computer-Assisted Intervention, (2015), 234–241. https://doi.org/10.1007/978-3-319-24574-4_28
    [28] C. Li, Y. Tan, W. Chen, X. Luo, Y. Gao, X. Jia, et al., Attention Unet++: A nested attention-aware U-Net for liver CT image segmentation, in IEEE International Conference on Image Processing, (2020), 345–349. https://doi.org/10.1109/ICIP40778.2020.9190761
    [29] H. Huang, L. Lin, R. Tong, H. Hu, Q. Zhang, Y. Iwamoto, et al., Unet 3+: A full-scale connected unet for medical image segmentation, in IEEE International Conference on Acoustics, Speech and Signal Processing, (2020), 1055–1059. https://doi.org/10.1109/ICASSP40776.2020.9053405
    [30] H. Seo, C. Huang, M. Bassenne, R. Xiao, L. Xing, Modified U-Net (mU-Net) with incorporation of object-dependent high level features for improved liver and liver-tumor segmentation in CT images, IEEE Trans. Med. Imaging, 39 (2019), 1316–1325. https://doi.org/10.1109/TMI.2019.2948320 doi: 10.1109/TMI.2019.2948320
    [31] D. T. Kushnure, S. N. Talbar, MS-UNet: A multi-scale UNet with feature recalibration approach for automatic liver and tumor segmentation in CT images, Comput. Med. Imaging Graphics, 89 (2021), 101885. https://doi.org/10.1016/j.compmedimag.2021.101885 doi: 10.1016/j.compmedimag.2021.101885
    [32] X. Xu, Q. Zhu, H. Ying, J. Li, X. Cai, S. Li, et al., A knowledge-guided framework for fine-grained classification of liver lesions based on multi-phase CT images, IEEE J. Biomed. Health Inf., 27 (2023), 386–396. https://doi.org/10.1109/JBHI.2022.3220788 doi: 10.1109/JBHI.2022.3220788
    [33] W. Shi, S. Kuang, S. Cao, B. Hu, S. Xie, S. Chen, et al., Deep learning assisted differentiation of hepatocellular carcinoma from focal liver lesions: choice of four-phase and three-phase CT imaging protocol, Abdom. Radiol., 45 (2020), 2688–2697. https://doi.org/10.1007/s00261-020-02485-8 doi: 10.1007/s00261-020-02485-8
    [34] Y. Xu, M. Cai, L. Lin, Y. Zhang, H. Hu, Z. Peng, et al., PA-ResSeg: A phase attention residual network for liver tumor segmentation from multiphase CT images, Med. Phys., 48 (2021), 3752–3766. https://doi.org/10.1002/mp.14922 doi: 10.1002/mp.14922
    [35] I. R. Kamel, M. A. Choti, K. M. Horton, H. J. V. Braga, B. A. Birnbaum, E. K. Fishman, et al., Surgically staged focal liver lesions: accuracy and reproducibility of dual-phase helical CT for detection and characterization, Radiology, 227 (2003), 752–757. https://doi.org/10.1148/radiol.2273011768 doi: 10.1148/radiol.2273011768
    [36] F. Ouhmich, V. Agnus, V. Noblet, F. Heitz, P. Pessaux, Liver tissue segmentation in multiphase CT scans using cascaded convolutional neural networks, Int. J. Comput. Assisted Radiol. Surg., 14 (2019), 1275–1284. https://doi.org/10.1007/s11548-019-01989-z doi: 10.1007/s11548-019-01989-z
    [37] C. Sun, S. Guo, H. Zhang, J. Li, M. Chen, S. Ma, et al., Automatic segmentation of liver tumors from multiphase contrast-enhanced CT images based on FCNs, Artif. Intell. Med., 83 (2017), 58–66. https://doi.org/10.1016/j.artmed.2017.03.008 doi: 10.1016/j.artmed.2017.03.008
    [38] Y. Wu, Q. Zhou, H. Hu, G. Rong, Y. Li, S. Wang, Hepatic lesion segmentation by combining plain and contrast-enhanced CT images with modality weighted U-Net, in IEEE International Conference on Image Processing, (2019), 255–259. https://doi.org/10.1109/ICIP.2019.8802942
    [39] Y. Zhang, C. Peng, L. Peng, H. Huang, R. Tong, L. Lin, et al., Multi-phase liver tumor segmentation with spatial aggregation and uncertain region inpainting, in International Conference on Medical Image Computing and Computer-Assisted Intervention, (2021), 68–77. https://doi.org/10.1007/978-3-030-87193-2_7
    [40] A. Vaswani, N. Shazeer, N. Parmar, J. Uszkoreit, L. Jones, A. N. Gomez, et al., Attention is all you need, in Advances in Neural Information Processing Systems, 30 (2017).
    [41] L. Wang, X. Wang, B. Zhang, X. Huang, C. Bai, M. Xia, et al., Multi-scale Hierarchical Transformer structure for 3D medical image segmentation, in IEEE International Conference on Bioinformatics and Biomedicine, (2021), 1542–1545. https://doi.org/10.1109/BIBM52615.2021.9669799
    [42] H. Cao, Y. Wang, J. Chen, D. Jiang, X. Zhang, Q. Tian, et al., Swin-unet: Unet-like pure transformer for medical image segmentation, in European Conference on Computer Vision, (2021), 205–218. https://doi.org/10.1007/978-3-031-25066-8_9
    [43] J. Chen, Y. Lu, Q. Yu, X. Luo, E. Adeli, Y. Wang, et al., Transunet: Transformers make strong encoders for medical image segmentation, preprint, arXiv: 2102.04306. https://doi.org/10.48550/arXiv.2102.04306
    [44] H. Xiao, L. Li, Q. Liu, X. Zhu, Q. Zhang, Transformers in medical image segmentation: A review, Biomed. Signal Process., 84 (2023), 104791. https://doi.org/10.1016/j.bspc.2023.104791 doi: 10.1016/j.bspc.2023.104791
    [45] K. He, C. Gan, Z. Li, I. Rekik, Z. Yin, W. Ji, et al., Transformers in medical image analysis, Intell. Med., 3 (2023), 59–78. https://doi.org/10.1016/j.imed.2022.07.002 doi: 10.1016/j.imed.2022.07.002
    [46] Y. Xu, X. He, G. Xu, G. Qi, K. Yu, L. Yin, et al., A medical image segmentation method based on multi-dimensional statistical features, Front. Neurosci., 16 (2022), 1009581. https://doi.org/10.3389/fnins.2022.1009581 doi: 10.3389/fnins.2022.1009581
    [47] X. He, G. Qi, Z. Zhu, Y. Li, B. Cong, L. Bai, Medical image segmentation method based on multi-feature interaction and fusion over cloud computing, Simul. Modell. Pract. Theory, 126 (2023), 102769. https://doi.org/10.1016/j.simpat.2023.102769 doi: 10.1016/j.simpat.2023.102769
    [48] A. Hatamizadeh, V. Nath, Y. Tang, D. Yang, H. R. Roth, D. Xu, Swin unetr: Swin transformers for semantic segmentation of brain tumors in MRI images, in International Conference on Medical Image Computing and Computer-Assisted Intervention, (2021), 272–284. https://doi.org/10.1007/978-3-031-08999-2_22
    [49] Z. Zhu, X. He, G. Qi, Y. Li, B. Cong, Y. Liu, Brain tumor segmentation based on the fusion of deep semantics and edge information in multimodal MRI, Inf. Fusion, 91 (2023), 376–387. https://doi.org/10.1016/j.inffus.2022.10.022 doi: 10.1016/j.inffus.2022.10.022
    [50] Y. Li, Z. Wang, L. Yin, Z. Zhu, G. Qi, Y. Liu, X-Net: a dual encoding–decoding method in medical image segmentation, Visual Comput., 39 (2023), 2223–2233. https://doi.org/10.1007/s00371-021-02328-7 doi: 10.1007/s00371-021-02328-7
    [51] J. M. J. Valanarasu, P. Oza, I. Hacihaliloglu, V. M. Patel, Medical Transformer: Gated axial-attention for medical image segmentation, in International Conference on Medical Image Computing and Computer-Assisted Intervention, (2021), 36–46. https://doi.org/10.1007/978-3-030-87193-2_4
    [52] E. Xie, W. Wang, Z. Yu, A. Anandkumar, J. M. Alvarez, P. Luo, SegFormer: Simple and efficient design for semantic segmentation with transformers, in Advances in Neural Information Processing Systems, 34 (2021), 12077–12090.
    [53] A. Dosovitskiy, L. Beyer, A. Kolesnikov, D. Weissenborn, X. Zhai, T. Unterthiner, et al., An image is worth 16x16 words: Transformers for image recognition at scale, in International Conference on Learning Representations, preprint, arXiv: 2010.11929. https://doi.org/10.48550/arXiv.2010.11929
    [54] C. Peng, Y. Zhang, J. Zheng, B. Li, J. Shen, M. Li, et al., IMⅡN: an inter-modality information interaction network for 3D multi-modal breast tumor segmentation, Comput. Med. Imaging Graphics, 95 (2022), 102021. https://doi.org/10.1016/j.compmedimag.2021.102021 doi: 10.1016/j.compmedimag.2021.102021
    [55] L. Yuan, Y. Chen, T. Wang, W. Yu, Y. Shi, Z. H. Jiang, et al., Tokens-to-token vit: Training vision transformers from scratch on imagenet, in Proceedings of the IEEE/CVF International Conference on Computer Vision, (2021), 558–567. https://doi.org/10.48550/arXiv.2101.11986
    [56] N. Liu, N. Zhang, K. Wan, L. Shao, J. Han, Visual saliency transformer, in Proceedings of the IEEE/CVF International Conference on Computer Vision, (2021), 4722–4732.
    [57] A. Paszke, S. Gross, S. Chintala, G. Chanan, E. Yang, Z. DeVito, et al., Automatic differentiation in pytorch, in Advances in Neural Information Processing Systems, 2017.
    [58] D. P. Kingma, J. Ba, Adam: A method for stochastic optimization, preprint, arXiv: 1412.6980. https://doi.org/10.48550/arXiv.1412.6980
    [59] W. Luo, Y. Li, R. Urtasun, R. Zemel, Understanding the effective receptive field in deep convolutional neural networks, in Advances in Neural Information Processing Systems, 29 (2016).
    [60] W. Zhou, W. Jian, X. Cen, L. Zhang, H. Guo, Z. Liu, et al., Prediction of microvascular invasion of hepatocellular carcinoma based on contrast-enhanced MR and 3D convolutional neural networks, Front. Oncol., 11 (2021), 588010. https://doi.org/10.3389/fonc.2021.588010 doi: 10.3389/fonc.2021.588010
    [61] X. Zhong, H. Long, L. Su, R. Zheng, W. Wang, Y. Duan, et al., Radiomics models for preoperative prediction of microvascular invasion in hepatocellular carcinoma: a systematic review and meta-analysis, Abdom. Radiol., 47 (2022), 2071–2088. https://doi.org/10.1007/s00261-022-03496-3 doi: 10.1007/s00261-022-03496-3
    [62] K. Bera, N. Braman, A. Gupta, V. Velcheti, A. Madabhushi, Predicting cancer outcomes with radiomics and artificial intelligence in radiology, Nat. Rev. Clin. Oncol., 19 (2022), 132–146. https://doi.org/10.1038/s41571-021-00560-7 doi: 10.1038/s41571-021-00560-7
    [63] J. Liu, D. Cheng, Y. Liao, C. Luo, Q. Lei, X. Zhang, et al., Development of a magnetic resonance imaging-derived radiomics model to predict microvascular invasion in patients with hepatocellular carcinoma, Quant. Imaging Med. Surg., 13 (2023), 3948–3961. https://doi.org/10.21037/qims-22-1011 doi: 10.21037/qims-22-1011
    [64] J. J. M. Van Griethuysen, A. Fedorov, C. Parmar, A. Hosny, N. Aucoin, V. Narayan, et al., Computational radiomics system to decode the radiographic phenotype, Cancer Res., 77 (2017), e104–e107. https://doi.org/10.1158/0008-5472.CAN-17-0339 doi: 10.1158/0008-5472.CAN-17-0339
  • Reader Comments
  • © 2024 the Author(s), licensee AIMS Press. This is an open access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0)
通讯作者: 陈斌, bchen63@163.com
  • 1. 

    沈阳化工大学材料科学与工程学院 沈阳 110142

  1. 本站搜索
  2. 百度学术搜索
  3. 万方数据库搜索
  4. CNKI搜索

Metrics

Article views(2088) PDF downloads(143) Cited by(0)

Figures and Tables

Figures(7)  /  Tables(6)

/

DownLoad:  Full-Size Img  PowerPoint
Return
Return

Catalog