Ruza et al 2023a - Revision history

Rimni at 12:38, 1 September 2023

2023-09-01T12:38:28Z

Rimni at 12:37, 1 September 2023

2023-09-01T12:37:06Z

Rimni at 12:36, 1 September 2023

2023-09-01T12:36:26Z

Rimni at 12:34, 1 September 2023

2023-09-01T12:34:03Z

Rimni at 12:19, 1 September 2023

2023-09-01T12:19:54Z

Show changes

Rimni at 10:18, 1 September 2023

2023-09-01T10:18:26Z

Rimni at 10:13, 1 September 2023

2023-09-01T10:13:02Z

Rimni: /* 4.2 Evaluation metrics */

2023-09-01T10:11:30Z

‎4.2 Evaluation metrics

Rimni at 10:10, 1 September 2023

2023-09-01T10:10:33Z

Show changes

Rimni at 12:25, 30 August 2023

2023-08-30T12:25:44Z

@@ Line 373: / Line 373: @@
 ===4.2 Evaluation metrics===
-Precision, recall, <math display="inline">F1</math>-score, confidence interval (CI), and area under the curve were used to evaluate the effectiveness of the proposed method (AUC). Precision, recall, and the F1 score are specified precisely:
+Precision, recall, <math display="inline">F1</math>-score, confidence interval (CI), and area under the curve were used to evaluate the effectiveness of the proposed method (AUC). Precision, recall, and the <math display="inline">F1</math> score are specified precisely:
 {| class="formulaSCP" style="width: 100%;width: 100%;text-align: center;"
@@ Line 416: / Line 416: @@
-True-positive scores are represented by the symbol TP, whereas false-negative, true-negative, and false-positive scores are represented by the symbols <math display="inline">TN</math>, <math display="inline">FN</math>, and <math display="inline">FP</math>, respectively. The <math display="inline">F1</math> score can be a more helpful evaluation statistic due to the diversity of the benchmark dataset. The normal dataset consists of 70 photos, while the malignant dataset consists of 142 photos. In addition, a 95% confidence interval is considered a more meaningful assessment than specific performance measures. It has the potential to improve statistical power while capturing the reliability of the problem area. Finally, we represented the data by plotting the receiver operating characteristic curve and calculated the area under the receiver operating characteristic curve to measure the accuracy of the model (often abbreviated as AUC). The true positive rate (TPR)/call and false positive rate (FPR) are displayed on the ROC curve, where FPR is defined as follows:
+True-positive scores are represented by the symbol <math display="inline">TP</math>, whereas false-negative, true-negative, and false-positive scores are represented by the symbols <math display="inline">TN</math>, <math display="inline">FN</math>, and <math display="inline">FP</math>, respectively. The <math display="inline">F1</math> score can be a more helpful evaluation statistic due to the diversity of the benchmark dataset. The normal dataset consists of 70 photos, while the malignant dataset consists of 142 photos. In addition, a 95% confidence interval is considered a more meaningful assessment than specific performance measures. It has the potential to improve statistical power while capturing the reliability of the problem area. Finally, we represented the data by plotting the receiver operating characteristic curve and calculated the area under the receiver operating characteristic curve to measure the accuracy of the model (often abbreviated as AUC). The true positive rate (TPR)/call and false positive rate (FPR) are displayed on the ROC curve, where FPR is defined as follows:
 {| class="formulaSCP" style="width: 100%;width: 100%;text-align: center;"

@@ Line 410: / Line 410: @@
 {| style="vertical-align: top;margin:auto;width: 100%;"
 |-
-| <math display="inline">F1=2\, \times\, \displaystyle\frac{\hbox{Precision }\, \times\, \hbox{Recall }}{\textrm{Precision }\,+ \hbox{Recall }}</math>
+| <math display="inline">F1=2\, \times\, \displaystyle\frac{\hbox{Precision }\, \times\, \hbox{Recall }}{\textrm{Precision }\,+ \,\hbox{Recall }}</math>
 |}
 |  style="vertical-align: top;width: 5px;text-align: right;white-space: nowrap;"|(11)

@@ Line 373: / Line 373: @@
 ===4.2 Evaluation metrics===
-Precision, recall, F1-score, confidence interval (CI), and area under the curve were used to evaluate the effectiveness of the proposed method (AUC). Precision, recall, and the F1 score are specified precisely:
+Precision, recall, <math display="inline">F1</math>-score, confidence interval (CI), and area under the curve were used to evaluate the effectiveness of the proposed method (AUC). Precision, recall, and the F1 score are specified precisely:
 {| class="formulaSCP" style="width: 100%;width: 100%;text-align: center;"

@@ Line 60: / Line 60: @@
 To support this statement, Zhang et al. [14] combine the Graph Convolutional Network (GCN) with the CNN. Using these two advanced neural networks, the author was able to achieve an accuracy of <math display="inline">96.10\pm 1.60%</math>. Contributing to this accuracy are their 8-layer CNN and 14-fold data expansion approach. Accordingly, Maqsood et al. [16] added CNN features to improve the accuracy. The authors introduce a new method called transferable texture convolutional neural network (TTCNN) to improve the accuracy of disease detection. TTCNN consists of only three convolutional layers and one energy layer. The performance is evaluated based on the deep properties of convolutional neural network models such as InceptionResNet-V2 and VGG-16. Sparse image decomposition convolution method is used to fuse all retrieved feature vectors, and then entropy-driven firefly method is used to select the best features.
-While Zhang et al. [14], Maqsood et al. [16] focus on combining CNN features with other models, there are also researchers who include a CNN feature alone in their research, such as in Albalawi et al. [15] and Tsochatzidis et al. [17]. Albalawi et al. [15] use a CNN classifier to classify the obtained features. The model used K-means to analyze mammograms for mass using texture information. The research proposed to use ResNet to improve breast cancer mammograms. Also, Salama and  Aly [18] used ResNet50 in their research by using MIAS and the DDSM database and combining ResNet50 with a modified segmentation of UNet. In this research, the authors achieved 95.63% accuracy.
+While Zhang et al. [14] and Maqsood et al. [16] focus on combining CNN features with other models, there are also researchers who include a CNN feature alone in their research, such as in Albalawi et al. [15] and Tsochatzidis et al. [17]. Albalawi et al. [15] use a CNN classifier to classify the obtained features. The model used K-means to analyze mammograms for mass using texture information. The research proposed to use ResNet to improve breast cancer mammograms. Also, Salama and  Aly [18] used ResNet50 in their research by using MIAS and the DDSM database and combining ResNet50 with a modified segmentation of UNet. In this research, the authors achieved 95.63% accuracy.
 In summary, all the results reviewed here support the hypothesis that CNN and deep learning methods have improved the accuracy of a model. [[#tab-1|Table 1]] shows that some works combine their model with existing CNN models, e.g., in Zhang et al. [14] and Maqsood et al. [16]. In  Albalawi et al. [15], Salama and  Aly [18] and Tsochatzidis et al. [19], these researchers focus on developing their own CNN models. All the presented works are able to achieve high accuracy. In contrast, this work presents a novel method for breast cancer mass detection in mammography that differs from all other mentioned methods. We provide new insights about the pre-trained EfficientNet, a proven method for diagnosing breast cancer using huge amounts of medical image data. EfficientNet is a state-of-the-art deep learning architecture that has been shown to achieve outstanding results in many image classification tasks while using fewer parameters than previous models.

@@ Line 410: / Line 410: @@
 {| style="vertical-align: top;margin:auto;width: 100%;"
 |-
-| <math display="inline">F1=2\, x\, \displaystyle\frac{\hbox{Precision }\, x\, \hbox{Recall }}{\textrm{Precision }\,+ \hbox{Recall }}</math>
+| <math display="inline">F1=2\, \times\, \displaystyle\frac{\hbox{Precision }\, \times\, \hbox{Recall }}{\textrm{Precision }\,+ \hbox{Recall }}</math>
 |}
 |  style="vertical-align: top;width: 5px;text-align: right;white-space: nowrap;"|(11)

@@ Line 340: / Line 340: @@
 <div class="center" style="font-size: 75%;">'''Table 3'''. Training and testing image distribution</div>
-<div id='tab-1'></div>
+<div id='tab-4'></div>
 {| class="wikitable" style="margin: 1em auto 0.1em auto;border-collapse: collapse;font-size:85%;width:auto;"
 |-style="text-align:center"
@@ Line 364: / Line 364: @@
 |-style="text-align:center"
 ! Base model !! Image resolution !! Total parameter size !! Trainable !! Non-trainable
-|-
+|-style="text-align:center"
 |  EfficientNet B3
 |  300x300