Lung cancer is a deadly disease. An early diagnosis can significantly improve the patient survival and quality of life. One potential solution is using deep learning (DL) algorithms to automate the diagnosis using patient computed tomography (CT) scans. However, the limited availability of training data and the computational complexity of existing algorithms, as well as their reliance on high-performance systems, limit the potential of DL algorithms. To improve early lung cancer diagnoses, this study proposes a low-cost convolutional neural network (CNN) that uses a Mavage pooling technique to diagnose lung cancers.
The DL-based model uses five convolution layers with two residual connections and Mavage pooling layers. We trained the CNN using two publicly available datasets comprised of the IQ_OTH/NCCD dataset and the chest CT scan dataset. Additionally, we integrated the Mavage pooling in the AlexNet, ResNet-50, and GoogLeNet architectures to analyze the datasets. We evaluated the performance of the models based on accuracy and the area under the receiver operating characteristic curve (AUROC).
The CNN model achieved a 99.70% accuracy and a 99.66% AUROC when the scans were classified as either cancerous or non-cancerous. It achieved a 90.24% accuracy and a 94.63% AUROC when the scans were classified as containing either normal, benign, or malignant nodules. It achieved a 95.56% accuracy and a 99.37% AUROC when lung cancers were classified. Additionally, the results indicated that the diagnostic abilities of AlexNet, ResNet-50, and GoogLeNet were improved with the introduction of the Mavage pooling technique.
This study shows that a low-cost CNN can effectively diagnose lung cancers from patient CT scans. Utilizing Mavage pooling technique significantly improves the CNN diagnostic capabilities.
The code is available at: https://github.com/Saintcodded/Mavage-Pooling.git
Citation: Ayomide Abe, Mpumelelo Nyathi, Akintunde Okunade. Lung cancer diagnosis from computed tomography scans using convolutional neural network architecture with Mavage pooling technique[J]. AIMS Medical Science, 2025, 12(1): 13-27. doi: 10.3934/medsci.2025002
[1] | Muqeem Ahmad, Mobin Ahmad, Fatemah Mofarreh . Bi-slant lightlike submanifolds of golden semi-Riemannian manifolds. AIMS Mathematics, 2023, 8(8): 19526-19545. doi: 10.3934/math.2023996 |
[2] | Aliya Naaz Siddiqui, Meraj Ali Khan, Amira Ishan . Contact CR $ \delta $-invariant: an optimal estimate for Sasakian statistical manifolds. AIMS Mathematics, 2024, 9(10): 29220-29234. doi: 10.3934/math.20241416 |
[3] | Biswabismita Bag, Meraj Ali Khan, Tanumoy Pal, Shyamal Kumar Hui . Geometric analysis on warped product semi-slant submanifolds of a locally metallic Riemannian space form. AIMS Mathematics, 2025, 10(4): 8131-8143. doi: 10.3934/math.2025373 |
[4] | Mehmet Gülbahar . Qualar curvatures of pseudo Riemannian manifolds and pseudo Riemannian submanifolds. AIMS Mathematics, 2021, 6(2): 1366-1376. doi: 10.3934/math.2021085 |
[5] | Oğuzhan Bahadır . On lightlike geometry of indefinite Sasakian statistical manifolds. AIMS Mathematics, 2021, 6(11): 12845-12862. doi: 10.3934/math.2021741 |
[6] | Richa Agarwal, Fatemah Mofarreh, Sarvesh Kumar Yadav, Shahid Ali, Abdul Haseeb . On Riemannian warped-twisted product submersions. AIMS Mathematics, 2024, 9(2): 2925-2937. doi: 10.3934/math.2024144 |
[7] | Fatimah Alghamdi, Fatemah Mofarreh, Akram Ali, Mohamed Lemine Bouleryah . Some rigidity theorems for totally real submanifolds in complex space forms. AIMS Mathematics, 2025, 10(4): 8191-8202. doi: 10.3934/math.2025376 |
[8] | Fatemah Mofarreh, S. K. Srivastava, Anuj Kumar, Akram Ali . Geometric inequalities of $ \mathcal{PR} $-warped product submanifold in para-Kenmotsu manifold. AIMS Mathematics, 2022, 7(10): 19481-19509. doi: 10.3934/math.20221069 |
[9] | Mehmet Atçeken, Tuğba Mert . Characterizations for totally geodesic submanifolds of a $ K $-paracontact manifold. AIMS Mathematics, 2021, 6(7): 7320-7332. doi: 10.3934/math.2021430 |
[10] | Yusuf Dogru . $ \eta $-Ricci-Bourguignon solitons with a semi-symmetric metric and semi-symmetric non-metric connection. AIMS Mathematics, 2023, 8(5): 11943-11952. doi: 10.3934/math.2023603 |
Lung cancer is a deadly disease. An early diagnosis can significantly improve the patient survival and quality of life. One potential solution is using deep learning (DL) algorithms to automate the diagnosis using patient computed tomography (CT) scans. However, the limited availability of training data and the computational complexity of existing algorithms, as well as their reliance on high-performance systems, limit the potential of DL algorithms. To improve early lung cancer diagnoses, this study proposes a low-cost convolutional neural network (CNN) that uses a Mavage pooling technique to diagnose lung cancers.
The DL-based model uses five convolution layers with two residual connections and Mavage pooling layers. We trained the CNN using two publicly available datasets comprised of the IQ_OTH/NCCD dataset and the chest CT scan dataset. Additionally, we integrated the Mavage pooling in the AlexNet, ResNet-50, and GoogLeNet architectures to analyze the datasets. We evaluated the performance of the models based on accuracy and the area under the receiver operating characteristic curve (AUROC).
The CNN model achieved a 99.70% accuracy and a 99.66% AUROC when the scans were classified as either cancerous or non-cancerous. It achieved a 90.24% accuracy and a 94.63% AUROC when the scans were classified as containing either normal, benign, or malignant nodules. It achieved a 95.56% accuracy and a 99.37% AUROC when lung cancers were classified. Additionally, the results indicated that the diagnostic abilities of AlexNet, ResNet-50, and GoogLeNet were improved with the introduction of the Mavage pooling technique.
This study shows that a low-cost CNN can effectively diagnose lung cancers from patient CT scans. Utilizing Mavage pooling technique significantly improves the CNN diagnostic capabilities.
The code is available at: https://github.com/Saintcodded/Mavage-Pooling.git
The concept of lightlike submanifolds in geometry was initially established and expounded upon in a work produced by Duggal and Bejancu [1]. A nondegenerate screen distribution was employed in order to produce a nonintersecting lightlike transversal vector bundle of the tangent bundle. They defined the CR-lightlike submanifold as a generalization of lightlike real hypersurfaces of indefinite Kaehler manifolds and showed that CR-lightlike submanifolds do not contain invariant and totally real lightlike submanifolds. Further, they defined and studied GCR-lightlike submanifolds of Kaehler manifolds as an umbrella of invariant submanifolds, screen real submanifolds, and CR-lightlike and SCR-lightlike submanifolds in [2,3], respectively. Subsequently, B. Sahin and R. Gunes investigated geodesic property of CR-lightlike submanifolds [4] and the integrability of distributions in CR-lightlike submanifolds [5]. In the year 2010, Duggal and Sahin published a book [6]pertaining to the field of differential geometry, specifically focusing on the study of lightlike submanifolds. This book provides a comprehensive examination of recent advancements in lightlike geometry, encompassing novel geometric findings, accompanied by rigorous proofs, and exploring their practical implications in the field of mathematical physics. The investigation of the geometric properties of lightlike hypersurfaces and lightlike submanifolds has been the subject of research in several studies (see [7,8,9,10,11,12,13,14]).
Crasmareanu and Hretcanu[15] created a special example of polynomial structure [16] on a differentiable manifold, and it is known as the golden structure (¯M,g). Hretcanu C. E. [17] explored Riemannian submanifolds with the golden structure. M. Ahmad and M. A. Qayyoom studied geometrical properties of Riemannian submanifolds with golden structure [18,19,20,21] and metallic structure [22,23]. The integrability of golden structures was examined by A. Gizer et al. [24]. Lightlike hypersurfaces of a golden semi-Riemannian manifold was investigated by N. Poyraz and E. Yasar [25]. The golden structure was also explored in the studies [26,27,28,29].
In this research, we investigate the CR-lightlike submanifolds of a golden semi-Riemannian manifold, drawing inspiration from the aforementioned studies. This paper has the following outlines: Some preliminaries of CR-lightlike submanifolds are defined in Section 2. We establish a number of properties of CR-lightlike submanifolds on golden semi-Riemannian manifolds in Section 3. In Section 4, we look into several CR-lightlike submanifolds characteristics that are totally umbilical. We provide a complex illustration of CR-lightlike submanifolds of a golden semi-Riemannian manifold in the final section.
Assume that (¯ℵ,g) is a semi-Riemannian manifold with (k+j)-dimension, k,j≥1, and g as a semi-Riemannian metric on ¯ℵ. We suppose that ¯ℵ is not a Riemannian manifold and the symbol q stands for the constant index of g.
[15] Let ¯ℵ be endowed with a tensor field ψ of type (1,1) such that
ψ2=ψ+I, | (2.1) |
where I represents the identity transformation on Γ(Υ¯ℵ). The structure ψ is referred to as a golden structure. A metric g is considered ψ-compatible if
g(ψγ,ζ)=g(γ,ψζ) | (2.2) |
for all γ, ζ vector fields on Γ(Υ¯ℵ), then (¯ℵ,g,ψ) is called a golden Riemannian manifold. If we substitute ψγ into γ in (2.2), then from (2.1) we have
g(ψγ,ψζ)=g(ψγ,ζ)+g(γ,ζ). | (2.3) |
for any γ,ζ∈Γ(Υ¯ℵ).
If (¯ℵ,g,ψ) is a golden Riemannian manifold and ψ is parallel with regard to the Levi-Civita connection ¯∇ on ¯ℵ:
¯∇ψ=0, | (2.4) |
then (¯ℵ,g,ψ) is referred to as a semi-Riemannian manifold with locally golden properties.
The golden structure is the particular case of metallic structure [22,23] with p=1, q=1 defined by
ψ2=pψ+qI, |
where p and q are positive integers.
[1] Consider the case where ℵ is a lightlike submanifold of k of ¯ℵ. There is the radical distribution, or Rad(Υℵ), on ℵ that applies to this situation such that Rad(Υℵ)=Υℵ∩Υℵ⊥, ∀ p∈ℵ. Since RadΥℵ has rank r≥0, ℵ is referred to as an r-lightlike submanifold of ¯ℵ. Assume that ℵ is a submanifold of ℵ that is r-lightlike. A screen distribution is what we refer to as the complementary distribution of a Rad distribution on Υℵ, then
Υℵ=RadΥℵ⊥S(Υℵ). |
As S(Υℵ) is a nondegenerate vector sub-bundle of Υ¯ℵ|ℵ, we have
Υ¯ℵ|ℵ=S(Υℵ)⊥S(Υℵ)⊥, |
where S(Υℵ)⊥ consists of the orthogonal vector sub-bundle that is complementary to S(Υℵ) in Υ¯ℵ|ℵ. S(Υℵ),S(Υℵ⊥) is an orthogonal direct decomposition, and they are nondegenerate.
S(Υℵ)⊥=S(Υℵ⊥)⊥S(Υℵ⊥)⊥. |
Let the vector bundle
tr(Υℵ)=ltr(Υℵ)⊥S(Υℵ⊥). |
Thus,
Υ¯ℵ=Υℵ⊕tr(Υℵ)=S(Υℵ)⊥S(Υℵ⊥)⊥(Rad(Υℵ)⊕ltr(Υℵ). |
Assume that the Levi-Civita connection is ¯∇ on ¯ℵ. We have
¯∇γζ=∇γζ+h(γ,ζ),∀γ,ζ∈Γ(Υℵ) | (2.5) |
and
¯∇γζ=−Ahζ+∇⊥γh,∀γ∈Γ(Υℵ)andh∈Γ(tr(Υℵ)), | (2.6) |
where {∇γζ,Ahγ} and {h(γ,ζ),∇⊥γh} belongs to Γ(Υℵ) and Γ(tr(Υℵ)), respectively.
Using projection L:tr(Υℵ)→ltr(Υℵ), and S:tr(Υℵ)→S(Υℵ⊥), we have
¯∇γζ=∇γζ+hl(γ,ζ)+hs(γ,ζ), | (2.7) |
¯∇γℵ=−Aℵγ+∇lγℵ+λs(γ,ℵ), | (2.8) |
and
¯∇γχ=−Aχγ+∇sγ+λl(γ,χ) | (2.9) |
for any γ,ζ∈Γ(Υℵ),ℵ∈Γ(ltr(Υℵ)), and χ∈Γ(S(Υℵ⊥)), where hl(γ,ζ)=Lh(γ,ζ),hs(γ,ζ)=Sh(γ,ζ),∇lγℵ,λl(γ,χ)∈Γ(ltr(Tℵ)),∇sγλs(γ,ℵ)∈Γ(S(Υℵ⊥)), and ∇γζ,Aℵγ,Aχγ∈Γ(Υℵ).
The projection morphism of Υℵ on the screen is represented by P, and we take the distribution into consideration.
∇γPζ=∇∗γPζ+h∗(γ,Pζ),∇γξ=−A∗ξγ+∇∗tγξ, | (2.10) |
where γ,ζ∈Γ(Υℵ),ξ∈Γ(Rad(Υℵ)).
Thus, we have the subsequent equation.
g(h∗(γ,Pζ),ℵ)=g(Aℵγ,Pζ), | (2.11) |
Consider that ¯∇ is a metric connection. We get
(∇γg)(ζ,η)=g(hl(γ,ζ),η)+g(hl(γ,ζη),ζ). | (2.12) |
Using the characteristics of a linear connection, we can obtain
(∇γhl)(ζ,η)=∇lγ(hl(ζ,η))−hl(¯∇γζ,η)−hl(ζ,¯∇γη), | (2.13) |
(∇γhs)(ζ,η)=∇sγ(hs(ζ,η))−hs(¯∇γζ,η)−hs(ζ,¯∇γη). | (2.14) |
Based on the description of a CR-lightlike submanifold in [4], we have
Υℵ=λ⊕λ′, |
where λ=Rad(Υℵ)⊥ψRad(Υℵ)⊥λ0.
S and Q stand for the projection on λ and λ′, respectively, then
ψγ=fγ+wγ |
for γ,ζ∈Γ(Υℵ), where fγ=ψSγ and wγ=ψQγ.
On the other hand, we have
ψζ=Bζ+Cζ |
for any ζ∈Γ(tr(Υℵ)), Bζ∈Γ(Υℵ) and Cζ∈Γ(tr(Υℵ)), unless ℵ1 and ℵ2 are denoted as ψL1 and ψL2, respectively.
Lemma 2.1. Assume that the screen distribution is totally geodesic and that ℵ is a CR-lightlike submanifold of the golden semi-Riemannian manifold, then ∇γζ∈Γ(S(ΥN)), where γ,ζ∈Γ(S(Υℵ)).
Proof. For γ,ζ∈Γ(S(Υℵ)),
g(∇γζ,ℵ)=g(¯∇γζ−h(γ,ζ),ℵ)=−g(ζ,¯∇γℵ). |
Using (2.8),
g(∇γζ,ℵ)=−g(ζ,−Aℵγ+∇⊥γℵ)=g(ζ,Aℵγ). |
Using (2.11),
g(∇γζ,ℵ)=g(h∗(γ,ζ),ℵ). |
Since screen distribution is totally geodesic, h∗(γ,ζ)=0,
g(¯∇γζ,ℵ)=0. |
Using Lemma 1.2 in [1] p.g. 142, we have
∇γζ∈Γ(S(Υℵ)), |
where γ,ζ∈Γ(S(Υℵ)).
Theorem 2.2. Assume that ℵ is a locally golden semi-Riemannian manifold ¯ℵ with CR-lightlike properties, then ∇γψγ=ψ∇γγ for γ∈Γ(λ0).
Proof. Assume that γ,ζ∈Γ(λ0). Using (2.5), we have
g(∇γψγ,ζ)=g(¯∇γψγ−h(γ,ψγ),ζ)g(∇γψγ,ζ)=g(ψ(¯∇γγ),ζ)g(∇γψγ,ζ)=g(ψ(∇γγ),ζ),g(∇γψγ−ψ(∇γγ),ζ)=0. |
Nondegeneracy of λ0 implies
∇γψγ=ψ(∇γγ), |
where γ∈Γ(λ0).
Definition 3.1. [4] A CR-lightlike submanifold of a golden semi-Riemannian manifold is mixed geodesic if h satisfies
h(γ,α)=0, |
where h stands for second fundamental form, γ∈Γ(λ), and α∈Γ(λ′).
For γ,ζ∈Γ(λ) and α,β∈Γ(λ′) if
h(γ,ζ)=0 |
and
h(α,β)=0, |
then it is known as λ-geodesic and λ′-geodesic, respectively.
Theorem 3.2. Assume ℵ is a CR-lightlike submanifold of ¯ℵ, which is a golden semi-Riemannian manifold. ℵ is totally geodesic if
(Lg)(γ,ζ)=0 |
and
(Lχg)(γ,ζ)=0 |
for α,β∈Γ(Υℵ),ξ∈Γ(Rad(Υℵ)), and χ∈Γ(S(Υℵ⊥)).
Proof. Since ℵ is totally geodesic, then
h(γ,ζ)=0 |
for γ,ζ∈Γ(Υℵ).
We know that h(γ,ζ)=0 if
g(h(γ,ζ),ξ)=0 |
and
g(h(γ,ζ),χ)=0. |
g(h(γ,ζ),ξ)=g(¯∇γζ−∇γζ,ξ)=−g(ζ,[γ,ξ]+¯∇ξγ=−g(ζ,[γ,ξ])+g(γ,[ξ,ζ])+g(¯∇ζξ,γ)=−(Lξg)(γ,ζ)+g(¯∇ζξ,γ)=−(Lξg)(γ,ζ)−g(ξ,h(γ,ζ)))2g(h(γ,ζ)=−(Lξg)(γ,ζ). |
Since g(h(γ,ζ),ξ)=0, we have
(Lξg)(γ,ζ)=0. |
Similarly,
g(h(γ,ζ),χ)=g(¯∇γζ−∇γζ,χ)=−g(ζ,[γ,χ])+g(γ,[χ,ζ])+g(¯∇ζχ,γ)=−(Lχg)(γ,ζ)+g(¯∇ζχ,γ)2g(h(γ,ζ),χ)=−(Lχg)(γ,ζ). |
Since g(h(γ,ζ),χ)=0, we get
(Lχg)(γ,ζ)=0 |
for χ∈Γ(S(Υℵ⊥)).
Lemma 3.3. Assume that ¯ℵ is a golden semi-Riemannian manifold whose submanifold ℵ is CR-lightlike, then
g(h(γ,ζ),χ)=g(Aχγ,ζ) |
for γ∈Γ(λ),ζ∈Γ(λ′) and χ∈Γ(S(Υℵ⊥)).
Proof. Using (2.5), we get
g(h(γ,ζ),χ)=g(¯∇γζ−∇γζ,χ)=g(ζ,¯∇γχ). |
From (2.9), it follows that
g(h(γ,ζ),χ)=−g(ζ,−Aχγ+∇sγχ+λs(γ,χ))=g(ζ,Aχγ)−g(ζ,∇sγχ)−g(ζ,λs(γ,χ))g(h(γ,ζ),χ)=g(ζ,Aχγ), |
where γ∈Γ(λ),ζ∈Γ(λ′),χ∈Γ(S(Υℵ⊥)).
Theorem 3.4. Assume that ℵ is a CR-lightlike submanifold of the golden semi-Riemannian manifold and ¯ℵ is mixed geodesic if
A∗ξγ∈Γ(λ0⊥ψL1) |
and
Aχγ∈Γ(λ0⊥Rad(Υℵ)⊥ψL1) |
for γ∈Γ(λ),ξ∈Γ(Rad(Υℵ)), and χ∈Γ(S(Υℵ⊥)).
Proof. For γ∈Γ(λ),ζ∈Γ(λ′), and χ∈Γ(S(Υℵ⊥)), we get
Using (2.5),
g(h(γ,ζ),ξ)=g(¯∇γζ−∇γζ,ξ)=−g(ζ,¯∇γξ). |
Again using (2.5), we obtain
g(h(γ,ζ),ξ)=−g(ζ,∇γξ+h(γ,ξ))=−g(ζ,∇γξ). |
Using (2.10), we have
g(h(γ,ζ),ξ)=−g(ζ,−A∗ξγ+∇∗tγξ)g(ζ,A∗ξγ)=0. |
Since the CR-lightlike submanifold ℵ is mixed geodesic, we have
g(h(γ,ζ),ξ)=0 |
⇒g(ζ,A∗ξγ)=0 |
⇒A∗ξγ∈Γ(λ0⊥ψL1), |
where γ∈Γ(λ),ζ∈Γ(λ′).
From (2.5), we get
g(h(γ,ζ),χ)=g(¯∇γζ−∇γζ,χ)=−g(ζ,¯∇γχ). |
From (2.9), we get
g(h(γ,ζ),χ)=−g(ζ,−Aχγ+∇sγχ+λl(γ,χ))g(h(γ,ζ),χ)=g(ζ,Aχγ). |
Since, ℵ is mixed geodesic, then g(h(γ,ζ),χ)=0
⇒g(ζ,Aχγ)=0. |
Aχγ∈Γ(λ0⊥Rad(Υℵ)⊥ψ1). |
Theorem 3.5. Suppose that ℵ is a CR-lightlike submanifold of a golden semi-Riemannian manifold ¯ℵ, then ℵ is λ′-geodesic if Aχη and A∗ξη have no component in ℵ2⊥ψRad(Υℵ) for η∈Γ(λ′),ξ∈Γ(Rad(Υℵ)), and χ∈Γ(S(Υℵ⊥)).
Proof. From (2.5), we obtain
g(h(η,β),χ)=g(¯∇ηβ−∇γζ,χ)=−¯g(∇γζ,χ), |
where χ,β∈Γ(λ′).
Using (2.9), we have
g(h(η,β),χ)=−g(β,−Aχη+∇sη+λl(η,χ))g(h(η,β),χ)=g(β,Aχη). | (3.1) |
Since ℵ is λ′-geodesic, then g(h(η,β),χ)=0.
From (3.1), we get
g(β,Aχη)=0. |
Now,
g(h(η,β),ξ)=g(¯∇ηβ−∇ηβ,ξ)=g(¯∇ηβ,ξ)=−g(β,¯∇ηξ). |
From (2.10), we get
g(h(η,β),ξ)=−g(η,−A∗ξη+∇∗tηξ)g(h(η,β),ξ)=g(A∗ξβ,η). |
Since ℵ is λ′- geodesic, then
g(h(η,β),ξ)=0 |
⇒g(A∗ξβ,η)=0. |
Thus, Aχη and A∗ξη have no component in M2⊥ψRad(Υℵ).
Lemma 3.6. Assume that ¯ℵ is a golden semi-Riemannian manifold that has a CR-lightlike submanifold ℵ. Due to the distribution's integrability, the following criteria hold.
(ⅰ) ψg(λl(ψγ,χ),ζ)−g(λl(γ,χ),ψζ)=g(Aχψγ,ζ)−g(Aχγ,ψζ),
(ⅱ) g(λl(ψγ),ξ)=g(Aχγ,ψξ),
(ⅲ) g(λl(γ,χ),ξ)=g(Aχψγ,ψξ)−g(Aχγ,ψξ),
where γ,ζ∈Γ(Υℵ),ξ∈Γ(Rad(Υℵ)), and χ∈Γ(S(Υℵ⊥)).
Proof. From Eq (2.9), we obtain
g(λl(ψγ,χ),ζ)=g(¯∇ψγχ+Aχψγ−∇sψγχ,ζ)=−g(χ,¯∇ψγζ)+g(Aχψγ,ζ). |
Using (2.5), we get
g(λl(ψγ,χ),ζ)=−g(χ,∇ψγζ+h(ψγ,ζ))+g(Aχψγ,ζ)=−g(χ,h(γ,ψζ))+g(Aχψγ,ζ). |
Again, using (2.5), we get
g(λl(ψγ,χ),ζ)=−g(χ,¯∇γψζ−∇γψζ)+g(Aχψγ,ζ)=g(¯∇γχ,ψζ)+g(Aχψγ,ζ). |
Using (2.9), we have
g(λl(ψγ,χ),ζ)=g(−Aχγ+∇sγχ+λl(γ,χ),ψζ)+g(λl(ψγ,χ),ζ)−g(λl(γ,χ),ψζ)=g(Aχψγ,ζ)−g(Aχγ,ψζ). |
(ⅱ) Using (2.9), we have
g(λl(ψγ,χ),ξ)=g(Aχψγ−∇sψγχ+∇ψγχ,ξ)=g(Aχψγ,ξ)−g(χ,¯∇ψγξ). |
Using (2.10), we get
g(λl(ψγ,χ),ξ)=g(Aχψγ,ξ)+g(χ,A∗ξψγ)−g(χ,∇∗tψγ,ξ)g(λl(ψγ),ξ)=g(Aχγ,ψξ). |
(ⅲ) Replacing ζ by ψξ in (ⅰ), we have
ψg(λl(ψγ,χ),ψξ)−g(λl(γ,χ),ψ2ξ)=g(Aχψγ,ψξ)−g(Aχγ,ψ2ξ). |
Using Definition 2.1 in [18] p.g. 9, we get
ψg(λl(ψγ,χ),ψξ)−g(λl(γ,χ),(ψ+I)ξ)=g(Aχψγ,ψξ)−g(Aχγ,(ψ+I)ξ)ψg(λl(ψγ,χ),ψξ)−g(λl(γ,χ),ψξ)−g(λl(γ,χ),ξ)=g(Aχψγ,ψξ)−g(Aχγ,ψξ)−g(Aχγ,ξ).g(λl(γ,χ),ξ)=g(Aχψγ,ψξ)−g(Aχγ,ψξ). |
Definition 4.1. [12] A CR-lightlike submanifold of a golden semi-Riemannian manifold is totally umbilical if there is a smooth transversal vector field H∈tr Γ(Υℵ) that satisfies
h(χ,η)=Hg(χ,η), |
where h is stands for second fundamental form and χ, η∈ Γ(Υℵ).
Theorem 4.2. Assume that the screen distribution is totally geodesic and that ℵ is a totally umbilical CR-lightlike submanifold of the golden semi-Riemannian manifold ¯ℵ, then
Aψηχ=Aψχη,∀χ,η∈Γλ′. |
Proof. Given that ¯ℵ is a golden semi-Riemannian manifold,
ψ¯∇ηχ=¯∇ηψχ. |
Using (2.5) and (2.6), we have
ψ(∇ηχ)+ψ(h(η,χ))=−Aψχη+∇tηψχ. | (4.1) |
Interchanging η and χ, we obtain
ψ(∇χη)+ψ(h(χ,η))=−Aψηχ+∇tχψη. | (4.2) |
Subtracting Eqs (4.1) and (4.2), we get
ψ(∇ηχ−∇χη)−∇tηψχ+∇tχψη=Aψηχ−Aψχη. | (4.3) |
Taking the inner product with γ∈Γ(λ0) in (4.3), we have
g(ψ(∇χη,γ)−g(ψ(∇χη,γ)=g(Aψηχ,γ)−g(Aψχη,γ).g(Aψηχ−Aψχη,γ)=g(∇χη,−ψγ)g(∇χη,ψγ). | (4.4) |
Now,
g(∇χη,ψγ)=g(¯∇χη−h(χ,η),ψγ)g(∇χη,ψγ)=−g(η,(¯∇χψ)γ−ψ(¯∇χγ)). |
Since ψ is parallel to ¯∇, i.e., ¯∇γψ=0,
g(∇χη,ψγ)=−ψ(¯∇χγ)). |
Using (2.7), we have
g(∇χη,ψγ)=−g(ψη,∇χγ+hs(χ,γ)+hl(χ,γ))g(∇χη,ψγ)=−g(ψη,∇χγ)−g(ψη,hs(χ,γ))−g(ψη,hl(χ,γ)). | (4.5) |
Since ℵ is a totally umbilical CR-lightlike submanifold and the screen distribution is totally geodesic,
hs(χ,γ)=Hsg(χ,γ)=0 |
and
hl(χ,γ)=Hlg(χ,γ)=0, |
where χ∈Γ(λ′) and γ∈Γ(λ0).
From (4.5), we have
g(∇χη,ψγ)=−g(ψη,∇χγ). |
From Lemma 2.1, we get
g(∇χη,ψγ)=0. |
Similarly,
g(∇ηχ,ψγ)=0 |
Using (4.4), we have
g(Aψηχ−Aψχη,γ)=0. |
Since λ0 is nondegenerate,
Aψηχ−Aψχη=0 |
⇒Aψηχ=Aψχη. |
Theorem 4.3. Let ℵ be the totally umbilical CR-lightlike submanifold of the golden semi-Riemannian manifold ¯ℵ. Consequently, ℵ's sectional curvature, which is CR-lightlike, vanishes, resulting in ¯K(π)=0, for the entire CR-lightlike section π.
Proof. We know that ℵ is a totally umbilical CR-lightlike submanifold of ¯ℵ, then from (2.13) and (2.14),
(∇γhl)(ζ,ω)=g(ζ,ω)∇lγHl−Hl{(∇γg)(ζ,ω)}, | (4.6) |
(∇γhs)(ζ,ω)=g(ζ,ω)∇sγHs−Hs{(∇γg)(ζ,ω)} | (4.7) |
for a CR-lightlike section π=γ∧ω,γ∈Γ(λ0),ω∈Γ(λ′).
From (2.12), we have (∇Ug)(ζ,ω)=0. Therefore, from (4.6) and (4.7), we get
(∇γhl)(ζ,ω)=g(ζ,ω)∇lγHl, | (4.8) |
(∇γhs)(ζ,ω)=g(ζ,ω)∇sγHs. | (4.9) |
Now, from (4.8) and (4.9), we get
{¯R(γ,ζ)ω}tr=g(ζ,ω)∇lγHl−g(γ,ω)∇lζHl+g(ζ,ω)λl(γ,Hs)−g(γ,ω)λl(ζ,Hs)+g(ζ,ω)∇sγHs−g(γ,ω)∇sζHs+g(ζ,ω)λs(γ,Hl)−g(γ,ω)λs(ζ,Hl). | (4.10) |
For any β∈Γ(tr(Υℵ)), from Equation (4.10), we get
¯R(γ,ζ,ω,β)=g(ζ,ω)g(∇lγHl,β)−g(γ,ω)g(∇lζHl,β)+g(ζ,ω)g(λl(γ,Hs),ζ)−g(γ,ω)g(λl(ζ,Hs),β)+g(ζ,ω)g(∇sγHs,β)−g(γ,ω)g(∇sζHs,β)+g(ζ,ω)g(λs(γ,Hl),β)−g(γ,ω)g(λs(ζ,Hl,β). |
R(γ,ω,ψγ,ψω)=g(ω,ψγ)g(∇lγHl,ψω)−g(γ,ψγ)g(∇lωHl,ψω)+g(ω,ψγ)g(λl(γ,Hs),ψω)−g(γ,ψγ)g(λl(ω,Hs),ψω)+g(ω,ψγ)g(∇sγHs,ψω)−g(γ,ψγ)g(∇sωHs,ψω)+g(ω,ψγ)g(λs(γ,Hl),ψω)−g(γ,ψγ)g(λs(ω,Hl,ψU). |
For any unit vectors γ∈Γ(λ) and ω∈Γ(λ′), we have
¯R(γ,ω,ψγ,ψω)=¯R(γ,ω,γ,ω)=0. |
We have
K(γ)=KN(γ∧ζ)=g(¯R(γ,ζ)ζ,γ), |
where
¯R(γ,ω,γ,ω)=g(¯R(γ,ω)γ,ω) |
or
¯R(γ,ω,ψγ,ψω)=g(¯R(γ,ω)ψγ,ψω) |
i.e.,
¯K(π)=0 |
for all CR-sections π.
Example 5.1. We consider a semi-Riemannian manifold R62 and a submanifold ℵ of co-dimension 2 in R62, given by equations
υ5=υ1cosα−υ2sinα−υ3z4tanα, |
υ6=υ1sinα−υ2cosα−υ3υ4, |
where α∈R−{π2+kπ; k∈z}. The structure on R62 is defined by
ψ(∂∂υ1,∂∂υ2,∂∂υ3,∂∂υ4,∂∂υ5,∂∂υ6)=(¯ϕ ∂∂υ1,¯ϕ∂∂υ2,ϕ∂∂υ3,ϕ∂∂υ4,ϕ∂∂υ5,ϕ∂∂υ6). |
Now,
ψ2(∂∂υ1,∂∂υ2,∂∂υ3,∂∂υ4,∂∂υ5,∂∂υ6)=((¯ϕ+1) ∂∂υ1,(¯ϕ+1)∂∂υ2,(ϕ+1)∂∂υ3,(ϕ+1)∂∂υ4, |
(ϕ+1)∂∂υ5,(ϕ+1)∂∂υ6) |
ψ2=ψ+I. |
It follows that (R62,ψ) is a golden semi-Reimannian manifold.
The tangent bundle Υℵ is spanned by
Z0=−sinα ∂∂υ5−cosα ∂∂υ6−ϕ ∂∂υ2, |
Z1=−ϕ sinα ∂∂υ5−ϕ cosα ∂∂υ6+ ∂∂υ2, |
Z2=∂∂υ5−¯ϕ sinα ∂∂υ2+∂∂υ1, |
Z3=−¯ϕ cosα ∂∂υ2+∂∂υ4+i∂∂υ6. |
Thus, ℵ is a 1-lightlike submanifold of R62 with RadΥℵ=Span{X0}. Using golden structure of R62, we obtain that X1=ψ(X0). Thus, ψ(RadΥℵ) is a distribution on ℵ. Hence, the ℵ is a CR-lightlike submanifold.
In general relativity, particularly in the context of the black hole theory, lightlike geometry finds its uses. An investigation is made into the geometry of the ℵ golden semi-Riemannian manifolds that are CR-lightlike in nature. There are many intriguing findings on completely umbilical and completely geodesic CR-lightlike submanifolds that are examined. We present a required condition for a CR-lightlike submanifold to be completely geodesic. Moreover, it is demonstrated that the sectional curvature K of an entirely umbilical CR-lightlike submanifold ℵ of a golden semi-Riemannian manifold ¯ℵ disappears.
The authors declare they have not used Artificial Intelligence (AI) tools in the creation of this article.
The present work (manuscript number IU/R&D/2022-MCN0001708) received financial assistance from Integral University in Lucknow, India as a part of the seed money project IUL/IIRC/SMP/2021/010. All of the authors would like to express their gratitude to the university for this support. The authors are highly grateful to editors and referees for their valuable comments and suggestions for improving the paper. The present manuscript represents the corrected version of preprint 10.48550/arXiv.2210.10445. The revised version incorporates the identities of all those who have made contributions, taking into account their respective skills and understanding.
Authors have no conflict of interests.
[1] |
Cruz CSD, Tanoue LT, Matthay RA (2011) Lung cancer: epidemiology, etiology, and prevention. Clin Chest Med 32: 605-644. https://doi.org/10.1016/j.ccm.2011.09.001 ![]() |
[2] |
Bray F, Ferlay J, Soerjomataram I, et al. (2018) Global cancer statistics 2018: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries. CA Cancer J Clin 68: 394-424. https://doi.org/10.3322/caac.21492 ![]() |
[3] |
Schabath MB, Cote ML (2019) Cancer progress and priorities: lung cancer. Cancer Epidemiol Biomarkers Prev 28: 1563-1579. https://doi.org/10.1158/1055-9965.EPI-19-0221 ![]() |
[4] |
Yoon SM, Shaikh T, Hallman M (2017) Therapeutic management options for stage III non-small cell lung cancer. World J Clin Oncol 8: 1-20. https://doi.org/10.5306/wjco.v8.i1.1 ![]() |
[5] |
Hoffman RM, Atallah RP, Struble RD, et al. (2020) Lung cancer screening with low-dose CT: a meta-analysis. J Gen Intern Med 35: 3015-3025. https://doi.org/10.1007/s11606-020-05951-7 ![]() |
[6] |
Silvestri GA, Goldman L, Tanner NT, et al. (2023) Outcomes from more than 1 million people screened for lung cancer with low-dose CT imaging. Chest 164: 241-251. https://doi.org/10.1016/j.chest.2023.02.003 ![]() |
[7] |
Shin HJ, Kim MS, Kho BG, et al. (2020) Delayed diagnosis of lung cancer due to misdiagnosis as worsening of sarcoidosis: a case report. BMC Pulm Med 20: 1-4. https://doi.org/10.1186/s12890-020-1105-2 ![]() |
[8] |
Del Ciello A, Franchi P, Contegiacomo A, et al. (2017) Missed lung cancer: when, where, and why?. Diagn Interv Radiol 23: 118-126. https://doi.org/10.5152/dir.2016.16187 ![]() |
[9] |
Friedland B (2009) Medicolegal issues related to cone beam CT. Semin Orthod 15: 77-84. https://doi.org/10.1053/j.sodo.2008.09.010 ![]() |
[10] |
Krupinski EA, Berbaum KS, Caldwell RT, et al. (2010) Long radiology workdays reduce detection and accommodation accuracy. J Am Coll Radiol 7: 698-704. https://doi.org/10.1016/j.jacr.2010.03.004 ![]() |
[11] |
Abujudeh HH, Boland GW, Kaewlai R, et al. (2010) Abdominal and pelvic computed tomography (CT) interpretation: discrepancy rates among experienced radiologists. Eur Radiol 20: 1952-1957. https://doi.org/10.1007/s00330-010-1763-1 ![]() |
[12] |
Jacobsen MM, Silverstein SC, Quinn M, et al. (2017) Timeliness of access to lung cancer diagnosis and treatment: a scoping literature review. Lung cancer 112: 156-164. https://doi.org/10.1016/j.lungcan.2017.08.011 ![]() |
[13] | Sathyakumar K, Munoz M, Singh J, et al. (2020) Automated lung cancer detection using artificial intelligence (AI) deep convolutional neural networks: a narrative literature review. Cureus 12: e10017. https://doi.org/10.7759/cureus.10017 |
[14] |
Huang S, Yang J, Shen N, et al. (2023) Artificial intelligence in lung cancer diagnosis and prognosis: current application and future perspective. Semin Cancer Biol 89: 30-37. https://doi.org/10.1016/j.semcancer.2023.01.006 ![]() |
[15] |
Ardila D, Kiraly AP, Bharadwaj S, et al. (2019) End-to-end lung cancer screening with three-dimensional deep learning on low-dose chest computed tomography. Nat Med 25: 954-961. https://doi.org/10.1038/s41591-019-0447-x ![]() |
[16] |
Alrahhal MS, Alqhtani E (2021) Deep learning-based system for detection of lung cancer using fusion of features. Int J Comput Sci Mobile Comput 10: 57-67. https://doi.org/10.47760/ijcsmc.2021.v10i02.009 ![]() |
[17] |
Huang X, Shan J, Vaidya V (2017) Lung nodule detection in CT using 3D convolutional neural networks. 2017 IEEE 14th International Symposium on Biomedical Imaging (ISBI 2017) : 379-383. https://doi.org/10.1109/ISBI.2017.7950542 ![]() |
[18] |
Guo Y, Song Q, Jiang M, et al. (2021) Histological subtypes classification of lung cancers on CT images using 3D deep learning and radiomics. Acad Radiol 28: e258-e266. https://doi.org/10.1016/j.acra.2020.06.010 ![]() |
[19] |
Cui X, Zheng S, Heuvelmans MA, et al. (2022) Performance of a deep learning-based lung nodule detection system as an alternative reader in a Chinese lung cancer screening program. Eur J Radiol 146: 110068. https://doi.org/10.1016/j.ejrad.2021.110068 ![]() |
[20] |
Dunn B, Pierobon M, Wei Q (2023) Automated classification of lung cancer subtypes using deep learning and CT-scan based radiomic analysis. Bioengineering 10: 690. https://doi.org/10.3390/bioengineering10060690 ![]() |
[21] |
de Margerie-Mellon C, Chassagnon G (2023) Artificial intelligence: a critical review of applications for lung nodule and lung cancer. Diagn Interv Imaging 104: 11-17. https://doi.org/10.1016/j.diii.2022.11.007 ![]() |
[22] |
Ahmed SF, Alam MSB, Hassan M, et al. (2023) Deep learning modelling techniques: current progress, applications, advantages, and challenges. Artif Intell Rev 56: 13521-13617. https://doi.org/10.1007/s10462-023-10466-8 ![]() |
[23] |
Zhang J, Xia Y, Zeng H, et al. (2018) NODULe: combining constrained multi-scale LoG filters with densely dilated 3D deep convolutional neural network for pulmonary nodule detection. Neurocomputing 317: 159-167. https://doi.org/10.1016/j.neucom.2018.08.022 ![]() |
[24] | AL-Huseiny MS, Sajit AS (2021) Transfer learning with GoogLeNet for detection of lung cancer. Indones J Electr Eng Comput Sci 22: 1078-1086. https://doi.org/10.11591/ijeecs.v22.i2.pp1078-1086 |
[25] |
Sakshiwala, Singh MP (2023) A new framework for multi-scale CNN-based malignancy classification of pulmonary lung nodules. J Ambient Intell Human Comput 14: 4675-4683. https://doi.org/10.1007/s12652-022-04368-w ![]() |
[26] |
Mamun M, Mahmud MI, Meherin M, et al. (2023) LCDctCNN: lung cancer diagnosis of CT scan images using CNN based model. 2023 10th International Conference on Signal Processing and Integrated Networks (SPIN) : 205-212. https://doi.org/10.1109/SPIN57001.2023.10116075 ![]() |
[27] | Krizhevsky A, Sutskever I, Hinton GE (2012) Imagenet classification with deep convolutional neural networks. Adv Neural Inf Process Syst 25. |
[28] | Hua KL, Hsu CH, Hidayati SC, et al. (2015) Computer-aided classification of lung nodules on computed tomography images via deep learning technique. Onco Targets Ther 8: 2015-2022. https://doi.org/10.2147/OTT.S80733 |
[29] | Ronneberger O, Fischer P, Brox T (2015) U-net: Convolutional networks for biomedical image segmentation. Medical Image Computing and Computer-Assisted Intervention–MICCAI 2015 . Springer International Publishing 234-241. https://doi.org/10.1007/978-3-319-24574-4_28 |
[30] |
Gulshan V, Peng L, Coram M, et al. (2016) Development and validation of a deep learning algorithm for detection of diabetic retinopathy in retinal fundus photographs. JAMA 316: 2402-2410. https://doi.org/10.1001/jama.2016.17216 ![]() |
[31] |
Kaul V, Enslin S, Gross SA (2020) History of artificial intelligence in medicine. Gastrointest Endosc 92: 807-812. https://doi.org/10.1016/j.gie.2020.06.040 ![]() |
[32] |
Esteva A, Kuprel B, Novoa RA, et al. (2017) Dermatologist-level classification of skin cancer with deep neural networks. Nature 542: 115-118. https://doi.org/10.1038/nature21056 ![]() |
[33] |
Saouli R, Akil M, Kachouri R (2018) Fully automatic brain tumor segmentation using end-to-end incremental deep neural networks in MRI images. Comput Methods Programs Biomed 166: 39-49. https://doi.org/10.1016/j.cmpb.2018.09.007 ![]() |
[34] |
Lorenzo PR, Nalepa J, Bobek-Billewicz B, et al. (2019) Segmenting brain tumors from FLAIR MRI using fully convolutional neural networks. Comput Methods Programs Biomed 176: 135-148. https://doi.org/10.1016/j.cmpb.2019.05.006 ![]() |
[35] |
Moitra D, Mandal RK (2019) Automated AJCC staging of non-small cell lung cancer (NSCLC) using deep convolutional neural network (CNN) and recurrent neural network (RNN). Health Inf Sci Syst 7: 1-12. https://doi.org/10.1007/s13755-019-0077-1 ![]() |
[36] |
Chaunzwa TL, Hosny A, Xu Y, et al. (2021) Deep learning classification of lung cancer histology using CT images. Sci Rep 11: 1-12. https://doi.org/10.1038/s41598-021-84630-x ![]() |
[37] |
Anari S, Tataei Sarshar N, Mahjoori N, et al. (2022) Review of deep learning approaches for thyroid cancer diagnosis. Math Probl Eng 2022: 5052435. https://doi.org/10.1155/2022/5052435 ![]() |
[38] |
Painuli D, Bhardwaj S, Köse U (2022) Recent advancement in cancer diagnosis using machine learning and deep learning techniques: a comprehensive review. Comput Biol Med 146: 105580. https://doi.org/10.1016/j.compbiomed.2022.105580 ![]() |
[39] |
Hosseini SH, Monsefi R, Shadroo S (2024) Deep learning applications for lung cancer diagnosis: a systematic review. Multimed Tools Appl 83: 14305-14335. https://doi.org/10.1007/s11042-023-16046-w ![]() |
[40] |
Aamir M, Rahman Z, Abro WA, et al. (2023) Brain tumor classification utilizing deep features derived from high-quality regions in MRI images. Biomed Signal Proces 85: 104988. https://doi.org/10.1016/j.bspc.2023.104988 ![]() |
[41] |
Sun M, Song Z, Jiang X, et al. (2017) Learning pooling for convolutional neural network. Neurocomputing 224: 96-104. https://doi.org/10.1016/j.neucom.2016.10.049 ![]() |
[42] |
Kumar RL, Kakarla J, Isunuri BV, et al. (2021) Multi-class brain tumor classification using residual network and global average pooling. Multimed Tools Appl 80: 13429-13438. https://doi.org/10.1007/s11042-020-10335-4 ![]() |
[43] |
Zafar A, Aamir M, Mohd Nawi N, et al. (2022) A comparison of pooling methods for convolutional neural networks. Appl Sci 12: 8643. https://doi.org/10.3390/app12178643 ![]() |
[44] |
Nirthika R, Manivannan S, Ramanan A, et al. (2022) Pooling in convolutional neural networks for medical image analysis: a survey and an empirical study. Neural Comput Appl 34: 5321-5347. https://doi.org/10.1007/s00521-022-06953-8 ![]() |
[45] |
Xiong W, Zhang L, Du B, et al. (2017) Combining local and global: rich and robust feature pooling for visual recognition. Pattern Recogn 62: 225-235. https://doi.org/10.1016/j.patcog.2016.08.006 ![]() |
[46] |
Dogan Y (2023) A new global pooling method for deep neural networks: Global average of top-k max-pooling. Trait Signal 40: 577-587. https://doi.org/10.18280/ts.400216 ![]() |
[47] |
Nirthika R, Manivannan S, Ramanan A, et al. (2022) Pooling in convolutional neural networks for medical image analysis: a survey and an empirical study. Neural Comput Applic 34: 5321-5347. https://doi.org/10.1007/s00521-022-06953-8 ![]() |
[48] |
Abuqaddom I, Mahafzah BA, Faris H (2021) Oriented stochastic loss descent algorithm to train very deep multi-layer neural networks without vanishing gradients. Knowledge-Based Systems 230: 107391. https://doi.org/10.1016/j.knosys.2021.107391 ![]() |
[49] |
LeCun Y, Bottou L, Bengio Y, et al. (1998) Gradient-based learning applied to document recognition. Proc IEEE 86: 2278-2324. https://doi.org/10.1109/5.726791 ![]() |
[50] | Sabri N, Hamed HNA, Ibrahim Z, et al. (2020) A comparison between average and max-pooling in convolutional neural network for scoliosis classification. Int J 9. https://doi.org/10.30534/ijatcse/2020/9791.42020 |
[51] |
Hyun J, Seong H, Kim E (2021) Universal pooling–a new pooling method for convolutional neural networks. Expert Syst Appl 180: 115084. https://doi.org/10.1016/j.eswa.2021.115084 ![]() |
[52] |
Özdemir C (2023) Avg-topk: a new pooling method for convolutional neural networks. Expert Syst Appl 223: 119892. https://doi.org/10.1016/j.eswa.2023.119892 ![]() |
[53] |
Zhou Q, Qu Z, Cao C (2021) Mixed pooling and richer attention feature fusion for crack detection. Pattern Recogn Lett 145: 96-102. https://doi.org/10.1016/j.patrec.2021.02.005 ![]() |
[54] | Hou Q, Zhang L, Cheng MM, et al. (2020) Strip pooling: Rethinking spatial pooling for scene parsing. Proceedings of the IEEE/CVF conference on computer vision and pattern recognition : 4003-4012. |
[55] | Kareem HF, AL-Husieny MS, Mohsen FY, et al. (2021) Evaluation of SVM performance in the detection of lung cancer in marked CT scan dataset. Indones J Electr Eng Comput Sci 21: 1731-1738. https://doi.org/10.11591/ijeecs.v21.i3.pp1731-1738 |
[56] | Alyasriy H (2020) The IQ-OTHNCCD lung cancer dataset. Mendeley Data . Available from: https://data.mendeley.com/datasets/bhmdr45bh2/1. Retrieved June 15, 2024 |
[57] | Hany M Chest CT-scan images dataset (2020). Available from: https://www.kaggle.com/datasets/mohamedhanyyy/chest-ctscan-images. Retrieved June 15, 2024 |
[58] | He K, Zhang X, Ren S, et al. (2016) Deep residual learning for image recognition. Proceedings of the IEEE conference on computer vision and pattern recognition : 770-778. |
[59] | Szegedy C, Liu W, Jia Y, et al. (2015) Going deeper with convolutions. Proceedings of the IEEE conference on computer vision and pattern recognition : 1-9. |
[60] | Paszke A, Gross S, Massa F, et al. (2019) Pytorch: an imperative style, high-performance deep learning library. Adv Neural Inf Process Syst 32. |
1. | Bang-Yen Chen, Majid Ali Choudhary, Afshan Perween, A Comprehensive Review of Golden Riemannian Manifolds, 2024, 13, 2075-1680, 724, 10.3390/axioms13100724 |