Score-CAM: Score-Weighted Visual Explanations for Convolutional Neural Networks

Wang, Haofan; Wang, Zifan; Du, Mengnan; Yang, Fan; Zhang, Zijian; Ding, Sirui; Mardziel, Piotr; Hu, Xia

doi:10.48550/arxiv.1910.01279

Cited by 25 publications

(25 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…We selected the top and last 500 samples from the CGMH Kaohsiung branch data according to the prediction scores from the best CNN models. In order to see where the CNN model learned from the MS peak patterns, we applied the selected samples to verify the important weight of each m/z peak of the CNN models using the Score-CAM technique (Wang et al, 2020a). First, we ranked the Score-CAM scores of each m/z peak, chose the highest 1% of peaks and conjugated the adjacent m/z peaks into a range.…”

Section: Feature Selection Proceduresmentioning

confidence: 99%

“…We applied the Score-CAM (Wang et al, 2020a) to examine the importance of m/z signals as informative features to affect the prediction performance of the best model for the top 500 VREfm and VSEfm prediction scores, respectively. Score-CAM was introduced to visually explain how the CNN models classified the MALDI-TOF MS signal patterns into two groups.…”

Section: Cnn Models Capture Important Features To Predict Vrefmmentioning

confidence: 99%

See 1 more Smart Citation

Efficiently Predicting Vancomycin Resistance of Enterococcus Faecium From MALDI-TOF MS Spectra Using a Deep Learning-Based Approach

Wang

Hsieh²,

Chung

et al. 2022

Front. Microbiol.

View full text Add to dashboard Cite

Matrix-assisted laser desorption ionization time-of-flight (MALDI-TOF) mass spectrometry (MS) has recently become a useful analytical approach for microbial identification. The presence and absence of specific peaks on MS spectra are commonly used to identify the bacterial species and predict antibiotic-resistant strains. However, the conventional approach using few single peaks would result in insufficient prediction power without using complete information of whole MS spectra. In the past few years, machine learning algorithms have been successfully applied to analyze the MALDI-TOF MS peaks pattern for rapid strain typing. In this study, we developed a convolutional neural network (CNN) method to deal with the complete information of MALDI-TOF MS spectra for detecting Enterococcus faecium, which is one of the leading pathogens in the world. We developed a CNN model to rapidly and accurately predict vancomycin-resistant Enterococcus faecium (VREfm) samples from the whole mass spectra profiles of clinical samples. The CNN models demonstrated good classification performances with the average area under the receiver operating characteristic curve (AUROC) of 0.887 when using external validation data independently. Additionally, we employed the score-class activation mapping (CAM) method to identify the important features of our CNN models and found some discriminative signals that can substantially contribute to detecting the ion of resistance. This study not only utilized the complete information of MALTI-TOF MS data directly but also provided a practical means for rapid detection of VREfm using a deep learning algorithm.

show abstract

Section: Feature Selection Proceduresmentioning

confidence: 99%

Section: Cnn Models Capture Important Features To Predict Vrefmmentioning

confidence: 99%

Efficiently Predicting Vancomycin Resistance of Enterococcus Faecium From MALDI-TOF MS Spectra Using a Deep Learning-Based Approach

Wang

Hsieh²,

Chung

et al. 2022

Front. Microbiol.

View full text Add to dashboard Cite

show abstract

“…To increase the reliability of the classification models, semantic segmentation models are used in sign language [27]. Visualization techniques [28][29][30] are also another method used in different tasks to understand whether the model is trained on useful features or not when performing classification or recognition task [26]. Thus, deep learning techniques along with different visualization techniques were adopted to this research for Bangla Sign Language Alphabets and Numerals recognition.…”

Section: Literature Reviewmentioning

confidence: 99%

“…For understanding the reasoning underlying CNN prediction, there are a variety of methodologies available, including Class Activation Mapping (CAM) [28], Grad-CAM++ [29], Smoothed Grad-CAM++ [30], and Score-CAM [28]. The visualization techniques help users to put trust on the CNN by understanding the learned features by CNN.…”

Section: Visualization Techniquementioning

confidence: 99%

See 1 more Smart Citation

Bangla Sign Language (BdSL) Alphabets and Numerals Classification Using a Deep Learning Model

Podder

Chowdhury

Tahir

et al. 2022

Sensors

View full text Add to dashboard Cite

A real-time Bangla Sign Language interpreter can enable more than 200 k hearing and speech-impaired people to the mainstream workforce in Bangladesh. Bangla Sign Language (BdSL) recognition and detection is a challenging topic in computer vision and deep learning research because sign language recognition accuracy may vary on the skin tone, hand orientation, and background. This research has used deep machine learning models for accurate and reliable BdSL Alphabets and Numerals using two well-suited and robust datasets. The dataset prepared in this study comprises of the largest image database for BdSL Alphabets and Numerals in order to reduce inter-class similarity while dealing with diverse image data, which comprises various backgrounds and skin tones. The papers compared classification with and without background images to determine the best working model for BdSL Alphabets and Numerals interpretation. The CNN model trained with the images that had a background was found to be more effective than without background. The hand detection portion in the segmentation approach must be more accurate in the hand detection process to boost the overall accuracy in the sign recognition. It was found that ResNet18 performed best with 99.99% accuracy, precision, F1 score, sensitivity, and 100% specificity, which outperforms the works in the literature for BdSL Alphabets and Numerals recognition. This dataset is made publicly available for researchers to support and encourage further research on Bangla Sign Language Interpretation so that the hearing and speech-impaired individuals can benefit from this research.

show abstract

Artificial Intelligence Detected the Relationship Between Nuclear Morphological Features and Molecular Abnormalities of Papillary Thyroid Carcinoma

Nishikawa,

Matsuzaki,

Takahashi

et al. 2024

Endocr Pathol

View full text Add to dashboard Cite

Score-CAM: Score-Weighted Visual Explanations for Convolutional Neural Networks

Cited by 25 publications

References 21 publications

Efficiently Predicting Vancomycin Resistance of Enterococcus Faecium From MALDI-TOF MS Spectra Using a Deep Learning-Based Approach

Efficiently Predicting Vancomycin Resistance of Enterococcus Faecium From MALDI-TOF MS Spectra Using a Deep Learning-Based Approach

Bangla Sign Language (BdSL) Alphabets and Numerals Classification Using a Deep Learning Model

Artificial Intelligence Detected the Relationship Between Nuclear Morphological Features and Molecular Abnormalities of Papillary Thyroid Carcinoma

Contact Info

Product

Resources

About