Rising incidence and mortality of cancer have led to an incremental amount of research in the field. To learn from preexisting data, it has become important to capture maximum information related to ...disease type, stage, treatment, and outcomes. Medical imaging reports are rich in this kind of information but are only present as free text. The extraction of information from such unstructured text reports is labor-intensive. The use of Natural Language Processing (NLP) tools to extract information from radiology reports can make it less time-consuming as well as more effective. In this study, we have developed and compared different models for the classification of lung carcinoma reports using clinical concepts. This study was approved by the institutional ethics committee as a retrospective study with a waiver of informed consent. A clinical concept-based classification pipeline for lung carcinoma radiology reports was developed using rule-based as well as machine learning models and compared. The machine learning models used were XGBoost and two more deep learning model architectures with bidirectional long short-term neural networks. A corpus consisting of 1700 radiology reports including computed tomography (CT) and positron emission tomography/computed tomography (PET/CT) reports were used for development and testing. Five hundred one radiology reports from MIMIC-III Clinical Database version 1.4 was used for external validation. The pipeline achieved an overall F1 score of 0.94 on the internal set and 0.74 on external validation with the rule-based algorithm using expert input giving the best performance. Among the machine learning models, the Bi-LSTM_dropout model performed better than the ML model using XGBoost and the Bi-LSTM_simple model on internal set, whereas on external validation, the Bi-LSTM_simple model performed relatively better than other 2. This pipeline can be used for clinical concept-based classification of radiology reports related to lung carcinoma from a huge corpus and also for automated annotation of these reports.
Cancer is a fatal disease and one of the leading causes of death worldwide. The cure rate in cancer treatment remains low; hence, cancer treatment is gradually shifting toward personalized treatment. ...Artificial intelligence (AI) and radiomics have been recognized as one of the potential areas of research in personalized medicine in oncology. Several researchers have identified the capabilities of AI and radiomics to characterize phenotype and there by predict the outcome of treatment in oncology. Although AI and radiomics have shown promising initial results in diagnosis and treatment in oncology, these technologies are also facing challenges of standardization and scalability. In the last few years, researchers have been trying to develop a research infrastructure for federated machine learning that increases the usability of Big Data for clinical research. These research infrastructures are based on the findable, accessible, interoperable, and reusable (i.e., FAIR) data principles. The India-Dutch "big imaging data approach for oncology in a Netherlands India collaboration" (BIONIC) is a jointly funded initiative by the Dutch Research Council (NWO) and the Indian Ministry of Electronics and Information Technology (MeitY), aiming to introduce radiomic-based research into clinical environments using federated machine learning on geographically dispersed collections of FAIR data. This article described a prototype end-to-end research infrastructure implemented through the BIONIC partnership into a leading cancer care public hospital in India.
Manual cohort building from radiology reports can be tedious. Natural Language Processing (NLP) can be used for automated cohort building. In this study, we have developed and validated an NLP ...approach based on deep learning (DL) to select lung cancer reports from a thoracic disease management group cohort.
4064 radiology reports (CT and PET/CT) of a thoracic disease management group reported between 2014 and 2016 were used. These reports were anonymised, cleaned, text normalized and split into a training, testing, and validation set. External validation was performed on radiology reports from the MIMIC-III clinical database. We used three DL models, namely, Bi-LSTM_simple, Bi-LSTM_dropout, and Pre-trained _BERT model to predict if a report concerned lung cancer. We studied the effect of minority oversampling on all models.
Without oversampling, the F1 scores at 95% CI for Bi-LSTM_simple, Bi-LSTM_dropout and BERT were 0.89, 0.90, and 0.86; with oversampling, the F1 scores were 0.94, 0.94, and 0.9, on internal validation. On external validation the F1-scores of Bi-LSTM_simple, Bi-LSTM_dropout and BERT models were 0.63, 0.77 and 0.80 without oversampling and 0.72, 0.78 and 0.77 with oversampling.
Pre-trained BERT model and Bi-LSTM_dropout models to predict a lung cancer report showed consistent performance on internal and external validation with the BERT model exhibiting superior performance. The overall F1 score decreased on external validation for both Bi-LSTM models with the Bi-LSTM_simple model showing a more significant drop. All models showed some improvement on minority oversampling.
Radiomics is the method of extracting high throughput mathematical and statistical features from medical images. These features have the potential to characterize the underlying pathology of the ...disease that is inappreciable to a trained human eye. There are several open-source and licensed tools to extract radiomic features such as pyradiomics, LIFEx, TexRAD, and RaCat. Although pyradiomics is a widely used radiomics package by researchers, this software is not very user-friendly and can be run using a command line. We have developed and validated the GUI tool, PyRadGUI to make the radiomics software easy to operate. This software adheres to IBSI radiomic feature definition and implements the radiomic pipeline in batch processing to extract radiomic features from multiple patient's data and stores it in a comma separated value (CSV). We validated PyRadGUI software with the existing pyradiomic pipeline.
Radiation therapy for lung cancer requires a gross tumour volume (GTV) to be carefully outlined by a skilled radiation oncologist (RO) to accurately pinpoint high radiation dose to a malignant mass ...while simultaneously minimizing radiation damage to adjacent normal tissues. This is manually intensive and tedious however, it is feasible to train a deep learning (DL) neural network that could assist ROs to delineate the GTV. However, DL trained on large openly accessible data sets might not perform well when applied to a superficially similar task but in a different clinical setting. In this work, we tested the performance of DL automatic lung GTV segmentation model trained on open-access Dutch data when used on Indian patients from a large public tertiary hospital, and hypothesized that
DL performance could be improved for a specific
clinical context, by means of modest transfer-learning on a small representative local subset.
X-ray computed tomography (CT) series in a public data set called "NSCLC-Radiomics" from The Cancer Imaging Archive was first used to train a DL-based lung GTV segmentation model (Model 1). Its performance was assessed using a different open access data set (Interobserver1) of Dutch subjects plus a private Indian data set from a local tertiary hospital (Test Set 2). Another Indian data set (Retrain Set 1) was used to fine-tune the former DL model using a transfer learning method. The Indian data sets were taken from CT of a hybrid scanner based in nuclear medicine, but the GTV was drawn by skilled Indian ROs. The final (after fine-tuning) model (Model 2) was then re-evaluated in "Interobserver1" and "Test Set 2." Dice similarity coefficient (DSC), precision, and recall were used as geometric segmentation performance metrics.
Model 1 trained exclusively on Dutch scans showed a significant fall in performance when tested on "Test Set 2." However, the DSC of Model 2 recovered by 14 percentage points when evaluated in the same test set. Precision and recall showed a similar rebound of performance after transfer learning, in spite of using a comparatively small sample size. The performance of both models, before and after the fine-tuning, did not significantly change the segmentation performance in "Interobserver1."
A large public open-access data set was used to train a generic DL model for lung GTV segmentation, but this did not perform well initially in the Indian clinical context. Using transfer learning methods, it was feasible to efficiently and easily fine-tune the generic model using only a small number of local examples from the Indian hospital. This led to a recovery of some of the geometric segmentation performance, but the tuning did not appear to affect the performance of the model in another open-access data set.
Caution is needed when using models trained on large volumes of international data in a local clinical setting, even when that training data set is of good quality. Minor differences in scan acquisition and clinician delineation preferences may result in an apparent drop in performance. However, DL models have the advantage of being efficiently "adapted" from a generic to a locally specific context, with only a small amount of fine-tuning by means of transfer learning on a small local institutional data set.
The world continues to face the COVID-19 crisis, and efforts are underway to integrate traditional medicine interventions for its effective management. The study aimed to determine the efficacy of ...the "AYURAKSHA" kit in terms of post-interventional percentage of COVID-19 IgG positivity, immunity levels, and quality of life (QoL) against COVID-19.
This was a non-randomized controlled, prospective intervention trial, done after the distribution of 80,000 AYURAKSHA kits (constituent of Sanshamani Vati, AYUSH Kadha, and Anu Taila) among Delhi police participants in India. Among 47,827 participants, the trial group (
= 101) was evaluated with the positivity percentage of IgG COVID-19 and Immune Status Questionnaire (ISQ) scores as a primary outcome and the WHO Quality of Life Brief Version (QOL BREF) scores along with hematological parameters as a secondary outcome in comparison to the control group (
= 71).
The data showed that the percentage of COVID-19 IgG positivity was significantly lower in the trial group (17.5 %) as compared to the control group (39.4 %,
= 0.003), indicating the lower risk (55.6%) of COVID-19 infection in the trial group. The decreased incidence (5.05%) and reduced mortality percentage (0.44%) of COVID-19 among Delhi police officers during peak times of the pandemic also corroborate our findings. The ISQ score and WHO-QOL BREF tool analysis showed the improved scores in the trial group when compared with the controls. Furthermore, no dysregulated blood profile and no increase in inflammation markers like C-reactive protein, erythrocyte sedimentation rate, Interleukin-6 (IL-6) were observed in the trial group. However, significantly enhanced (
= 0.027) IL-6 levels and random blood sugar levels were found in the control group (
= 0.032), compared to a trial group (
= 0.165) post-intervention. Importantly, the control group showed more significant (
= 0.0001) decline in lymphocyte subsets CD3
(% change = 21.04), CD4
(% change = 20.34) and CD8
(% change = 21.54) levels than in trial group, confirming more severity of COVID-19 infection in the control group.
The AYURAKSHA kit is associated with reduced COVID-19 positivity and with a better quality of life among the trial group. Hence, the study encourages in-depth research and future integration of traditional medicines for the prevention of the COVID-19 pandemic.
http://ctri.nic.in/, identifier: CTRI/2020/05/025171.
