MediScan: A Framework of U-Health and Prognostic AI Assessment on Medical Imaging

With technological advancements, remarkable progress has been made with the convergence of health sciences and Artificial Intelligence (AI). Modern health systems are proposed to ease patient diagnostics. However, the challenge is to provide AI-based precautions to patients and doctors for more accurate risk assessment. The proposed healthcare system aims to integrate patients, doctors, laboratories, pharmacies, and administrative personnel use cases and their primary functions onto a single platform. The proposed framework can also process microscopic images, CT scans, X-rays, and MRI to classify malignancy and give doctors a set of AI precautions for patient risk assessment. The proposed framework incorporates various DCNN models for identifying different forms of tumors and fractures in the human body i.e., brain, bones, lungs, kidneys, and skin, and generating precautions with the help of the Fined-Tuned Large Language Model (LLM) i.e., Generative Pretrained Transformer 4 (GPT-4). With enough training data, DCNN can learn highly representative, data-driven, hierarchical image features. The GPT-4 model is selected for generating precautions due to its explanation, reasoning, memory, and accuracy on prior medical assessments and research studies. Classification models are evaluated by classification report (i.e., Recall, Precision, F1 Score, Support, Accuracy, and Macro and Weighted Average) and confusion matrix and have shown robust performance compared to the conventional schemes.

Medical Images Segmentation for Lung Cancer Diagnosis Based on Deep Learning Architectures

Lung cancer presents one of the leading causes of mortalities for people around the world. Lung image analysis and segmentation are one of the primary steps used for early diagnosis of cancer. Handcrafted medical imaging segmentation presents a very time-consuming task for radiation oncologists. To address this problem, we propose in this work to develop a full and entire system used for early diagnosis of lung cancer in CT scan imaging. The proposed lung cancer diagnosis system is composed of two main parts: the first part is used for segmentation developed on top of the UNETR network, and the second part is a classification part used to classify the output segmentation part, either benign or malignant, developed on top of the self-supervised network. The proposed system presents a powerful tool for early diagnosing and combatting lung cancer using 3D-input CT scan data. Extensive experiments have been performed to contribute to better segmentation and classification results. Training and testing experiments have been performed using the Decathlon dataset. Experimental results have been conducted to new state-of-the-art performances: segmentation accuracy of 97.83%, and 98.77% as classification accuracy. The proposed system presents a new powerful tool to use for early diagnosing and combatting lung cancer using 3D-input CT scan data.

Deep Learning Techniques to Diagnose Lung Cancer

Medical imaging tools are essential in early-stage lung cancer diagnostics and the monitoring of lung cancer during treatment. Various medical imaging modalities, such as chest X-ray, magnetic resonance imaging, positron emission tomography, computed tomography, and molecular imaging techniques, have been extensively studied for lung cancer detection. These techniques have some limitations, including not classifying cancer images automatically, which is unsuitable for patients with other pathologies. It is urgently necessary to develop a sensitive and accurate approach to the early diagnosis of lung cancer. Deep learning is one of the fastest-growing topics in medical imaging, with rapidly emerging applications spanning medical image-based and textural data modalities. With the help of deep learning-based medical imaging tools, clinicians can detect and classify lung nodules more accurately and quickly. This paper presents the recent development of deep learning-based imaging techniques for early lung cancer detection.

Association of Diabetes Severity and Mortality with Lung Squamous Cell Carcinoma

Simple Summary

The survival impact of diabetes severity on lung cancer survival remains unclear. We performed head-to-head propensity score matching to estimate the survival impact of various adapted diabetes complications severity index (aDCSI) scores in patients with both diabetes and lung squamous cell carcinoma (SqCLC). The results indicated that diabetes severity (aDCSI ≥ 2) is an independent prognostic factor for the overall survival of patients with both diabetes and lung SqCLC who receive standard treatments. Prevention of diabetes progression is necessary for patients with diabetes; it affects not only diabetes control but also improves survival for patients with lung SqCLC.

Abstract

Purpose: The survival impact of diabetes severity on lung cancer remains unclear. We performed head-to-head propensity score matching to estimate the survival impact of various adapted diabetes complications severity index (aDCSI) scores in patients with both diabetes and lung squamous cell carcinoma (SqCLC). Patients and Methods: We enrolled patients with both diabetes and lung SqCLC and categorized them into the mild (aDCSI = 0–1) and moderate-to-severe (aDCSI ≥ 2) diabetes groups. The patients in both groups were matched at a 1:1 ratio. Results: the matching process yielded a final cohort of 5742 patients with both diabetes and lung SqCLC (2871 patients in the mild diabetes group and 2871 patients in the moderate-to-severe diabetes groups) who were eligible for further analysis. A multivariate Cox regression analysis revealed that the adjusted hazard ratio (aHR; 95% confidence interval) of all-cause death for the mild diabetes group relative to the moderate-to-severe diabetes group was 1.17 (1.08–1.28; p = 0.0005). Conclusion: severe diabetes (aDCSI ≥ 2) is an independent prognostic factor for OS among patients with both diabetes and lung SqCLC who receive standard treatments. Preventing diabetes progression is necessary for patients with diabetes because it not only supports diabetes control but also improves survival for patients with lung SqCLC.

Screening for fear of cancer recurrence: Instrument validation and current status in early stage lung cancer patients

BACKGROUND

Fear of cancer recurrence (FCR) is one of the most distressing concerns for cancer patients. A psychometrically validated brief scale is urgently needed for use in busy clinical oncology settings. This study aimed to (1) develop and validate the 7-item fear of cancer recurrence scale Chinese version (FCR7-C), and (2) explore the severity of FCR in post-operative early-stage lung cancer patients in Taiwan.

METHODS

Early-stage lung cancer patients were recruited from a medical center in Taiwan. The FCR7-C was evaluated for content and construct validity and internal consistency reliability. Construct validity of FCR7-C was determined by the empirically supported correlation and confirmatory factor analysis (CFA).

RESULTS

A total of 160 subjects were recruited. The FCR7-C was shown to have satisfactory content validity and internal consistency reliability (Cronbach's α = 0.9). The uni-dimensional structure was confirmed by CFA that showed a good fit for the model. The FCR7-C score correlates positively with the degree of most of the physical symptoms, anxiety, and depression, but correlates negatively with patient age, performance status, and quality of life. We found that 81.9% of patients reported at least some FCR, with a mean FCR severity of 15.18 (SD = 7.78).

CONCLUSION

FCR7-C is a brief screening tool with good psychometrics. Patients with early-stage lung cancer still revealed mild to moderate level of FCR. Applying the FCR7-C for to screen cancer patients' distress and further develop personalized psychological interventions would be strongly suggested.

Screening and Biosensor-Based Approaches for Lung Cancer Detection

Early diagnosis of lung cancer helps to reduce the cancer death rate significantly. Over the years, investigators worldwide have extensively investigated many screening modalities for lung cancer detection, including computerized tomography, chest X-ray, positron emission tomography, sputum cytology, magnetic resonance imaging and biopsy. However, these techniques are not suitable for patients with other pathologies. Developing a rapid and sensitive technique for early diagnosis of lung cancer is urgently needed. Biosensor-based techniques have been recently recommended as a rapid and cost-effective tool for early diagnosis of lung tumor markers. This paper reviews the recent development in screening and biosensor-based techniques for early lung cancer detection.

NRIP/DCAF6 stabilizes the androgen receptor protein by displacing DDB2 from the CUL4A-DDB1 E3 ligase complex in prostate cancer

Both nuclear receptor interaction protein (NRIP) and DNA damage binding protein 2 (DDB2) belong to the Cullin 4 (CUL4)-DDB1 binding protein family and are androgen receptor (AR)-interacting proteins. Here, we investigated the expression patterns of the NRIP, DDB2 and AR proteins in human prostate cancer tissues and found that the expression levels of NRIP and AR were higher, but the DDB2 level was lower, in prostate cancer tissues than in non-neoplastic controls, suggesting NRIP as a candidate tumor promoter and DDB2 as a tumor suppressor in prostate cancer. Furthermore, both NRIP and DDB2 shared the same AR binding domain; they were competitors for the AR, but not for DDB1 binding, in the AR-DDB2-DDB1-CUL4A complex. Conclusively, NRIP stabilizes the AR protein by displacing DDB2 from the AR-DDB2 complex. Consistent with our hypothesis, a specific expression pattern with high levels of NRIP and AR, together with a low level of DDB2, was found more frequently in the human prostate cancer tissues with a cribriform pattern than in non-cribriform tumors, suggesting that disruption of the balance between NRIP and DDB2 may change AR protein homeostasis and contribute to pathogenesis in certain aggressive types of prostate cancer.

The effect of gender on health-related quality of life and related factors in post-lobectomy lung-cancer patients

PURPOSE

While studies have documented gender differences by histologic type among lung cancer patients, the effect of these differences on the health-related quality of life (HRQoL) of post-lobectomy lungcancer patients and related factors remain uncertain. This study examines gender-specific HRQoL and related factors in post-lobectomy lung-cancer patients.

METHODS

A cross-sectional study design was applied. A convenience sample of 231 post-lobectomy lungcancer patients was recruited from the thoracic surgery outpatient departments of two teaching hospitals in Taipei, Taiwan from March to December 2012. Patients performed a spirometry test and completed instruments that included a Beck Depression Inventory-II, an Interpersonal Support Evaluation List, and the symptom and function scales of the Quality of Life Questionnaire. Data analysis used descriptive statistics, including mean and standard deviations, frequency, and percentage values. Independent-sample Student's t-tests and multivariate analyses were used for comparative purposes.

RESULTS

This study confirmed a significant gender effect on HRQoL and HRQoL-related factors such as marital status, religious affiliation, smoking status, histologic type, symptoms, pulmonary function, depression, and family support. Moreover, multivariate analysis found gender to be a significant determinant of the HRQoL aspects of physical functioning, emotional functioning, and cognitive functioning. Finally, results indicated that factors other than gender were also significant determinants of HRQoL.

CONCLUSION

Gender impacts the HRQoL and related factors of postoperative lung-cancer patients. Therefore, gender should be considered in assessing and addressing the individual care needs of these patients in order to attain optimal treatment outcomes.

Sex differences in early outcomes after lung cancer resection: analysis of the Society of Thoracic Surgeons General Thoracic Database

OBJECTIVES

Women with lung cancer have superior long-term survival outcomes compared with men, independent of stage. The cause of this disparity is unknown. For patients undergoing lung cancer resection, these survival differences could be due, in part, to relatively better perioperative outcomes for women. This study was undertaken to determine differences in perioperative outcomes after lung cancer surgery on the basis of sex.

METHODS

The Society of Thoracic Surgeons' General Thoracic Database was queried for all patients undergoing resection of lung cancer between 2002 and 2010. Postoperative complications were analyzed with respect to sex. Univariable analysis was performed, followed by multivariable modeling to determine significant risk factors for postoperative morbidity and mortality.

RESULTS

A total of 34,188 patients (16,643 men and 17,545 women) were considered. Univariable analysis demonstrated statistically significant differences in postoperative complications favoring women in all categories of postoperative complications. Women also had lower in-hospital and 30-day mortality (odds ratio, 0.56; 95% confidence interval, 0.44-0.71; P < .001). Multivariable analysis demonstrated that several preoperative conditions independently predicted 30-day mortality: male sex, increasing age, lower diffusion capacity, renal insufficiency, preoperative radiation therapy, cancer stage, extent of resection, and thoracotomy as surgical approach. Coronary artery disease was an independent predictor of mortality in women but not in men. Thoracotomy as the surgical approach and preoperative radiation therapy were predictive of mortality for men but not for women. Postoperative prolonged air leak and empyema predicted mortality in men but not in women.

CONCLUSIONS

Women have lower postoperative morbidity and mortality after lung cancer surgery. Some risk factors are sex-specific with regard to mortality. Further study is warranted to determine the cause of these differences and to determine their effect on survival.

Temporal trend analysis of avoidable mortality in Taiwan, 1971-2008: overall progress, with areas for further medical or public health investment

BACKGROUND

Avoidable mortality (AM), or "unnecessary untimely death," is considered an indicator of health care quality. We investigated trends in the age-standardized mortality rates (ASMRs) and associated standard expected years of life lost (SEYLL) for deaths amenable to medical care or public health measures in Taiwan from 1971-2008, with an emphasis on identifying areas where additional medical or public health investment may help reduce the burden of AM.

METHODS

Taiwan's ASMRs per 100,000 for AM and other causes of death were calculated using data from the National Death Certificate Registry in five-year bins from 1971 to 2008. SEYLL rates per 100,000 were calculated annually from 1971 to 2008 using the same data source.

RESULTS

ASMR for almost all AM and other causes of death declined dramatically from 1971 to 2008 except for lung cancer (16.6% and 7.4% increase among men and women, respectively) and breast cancer (109.8% increase among women). In the same period, SEYLL due to lung cancer increased from 269.2 to 555.7 for men and 249.7 to 342.5 for women. For women, SEYLL due to breast cancer increased from 263.5 in 1971 to 659.3 in 2008. There were gender-specific differences in the reduction (or increase) in AM rates, with women showing larger rates of reduction or smaller rates of increase. Among men, AM fell by 65.9% from 1971-1975 to 2006-2008, and deaths from other causes increased by 15.6%. Among women, AM and deaths from other causes fell by 80.8% and 59.8% respectively. SEYLL decreased, respectively among males and females, from 23,147.3 and 24,081.1 in 1971 to 11,261.8 and 5,929.6 in 2008.

CONCLUSION

From 1971 to 2008, Taiwan experienced a dramatic reduction in most AM and corresponding SEYLL except for lung cancer (for both males and females) and breast cancer (for females). Additional effort should be devoted to public health measures to combat the rising prevalence of smoking in Taiwan, which may be responsible for the increasing AM from lung cancer. If AM in breast cancer continues unabated in the future, greater policy emphasis on the early detection and treatment of breast cancer may also be warranted.

Association of thiazolidinediones with liver cancer and colorectal cancer in type 2 diabetes mellitus

The objective of this nationwide case-control study was to evaluate the risk of specific malignancy in diabetic patients who received thiazolidinediones (TZDs). A total of 606,583 type 2 diabetic patients, age 30 years and above, without a history of cancer were identified from the Taiwan National Health Insurance claims database during the period between January 1 2000 and December 31 2000. As of December 31 2007, patients with incident cancer of liver, colorectal, lung, and urinary bladder were included as cases and up to four age- and sex-matched controls were selected by risk-set sampling. Logistic regression models were applied to estimate the odds ratio (OR) and 95% confidence interval (CI) between TZDs and cancer incidence. A total of 10,741 liver cancer cases, 7,200 colorectal cancer cases, and 70,559 diabetic controls were included. A significantly lower risk of liver cancer incidence was found for any use of rosiglitazone (OR: 0.73, 95% CI: 0.65-0.81) or pioglitazone (OR: 0.83, 95% CI: 0.72-0.95), respectively. The protective effects were stronger for higher cumulative dosage and longer duration. For colorectal cancer, rosiglitazone, but not pioglitazone, was associated with a significantly reduced risk (OR: 0.86; 95% CI: 0.76-0.96). TZDs were not associated with lung and bladder cancer incidence, although a potential increased risk for bladder cancer with pioglitazone use ≥3 years could not be excluded (OR: 1.56; 95% CI: 0.51-4.74).

CONCLUSION

The use of pioglitazone and rosiglitazone is associated with a decreased liver cancer incidence in diabetic patients. The effects on occurrence of specific cancer types may be different for pioglitazone and rosiglitazone.

Factors related to daily life interference in lung cancer patients: a cross-sectional regression tree study

PURPOSE

To identify the symptom combination patterns and symptom severity levels that induce severe symptom interference in daily life activities, including physical and psychological activity interference in lung cancer patients.

METHODS

In a cross-sectional descriptive study using convenience sampling, 131 participants were recruited at a medical center in northern Taiwan. The Eastern Cooperative Oncology Group (ECOG) performance status was used to assess performance status, and the Taiwanese version of the M.D. Anderson Symptom Inventory (MDASI-T) was used to assess symptom severity and symptom interference in daily life activities including physical and psychological activities. Regression tree models were applied to examine variable combinations for symptom interference level in daily life activities, including physical and psychological activity interference.

RESULTS

Study results revealed that the performance status is the key discriminator of the symptom interference level in daily life and physical activities, but distress severity is the key discriminating factor of the symptom interference level in psychological activities. The performance status and distress severity, plus other factors, further specifically show the discrimination paths and interactions between the risk groups.

CONCLUSIONS

This study provided an alternative approach to identify low- and high-risk groups of symptom interference among lung cancer patients in Taiwan. Increased awareness and further understanding of the risk combinations and discriminate levels of symptom severity that induced high symptom interference offer different perspectives to develop patient-centered care planning for lung cancer patient rehabilitation.

Female gender is an independent prognostic factor in non-small-cell lung cancer: a meta-analysis

PURPOSE

It is not clear whether women with non-small-cell lung cancer (NSCLC) live significantly longer than men. Thus, we conducted a meta-analysis of published studies to quantitatively compare NSCLC survival data between genders.

MATERIALS AND METHODS

A MEDLINE Web search for computer-archived bibliographic data regarding overall survival differences between genders was performed. DerSimonian-Laird random effects analysis was used to estimate the pooled hazard ratio (HR).

RESULTS

We selected 39 articles as appropriate data sources, involving 86 800 patients including 32 701 women and 54 099 men. Combined HRs for women vs. men in studies using univariate and multivariate analyses respectively were 0.79 (p <0.0001) and 0.78 (p <0.0001). Pooled HRs for 3 study subgroups having (1) fewer than 30% stage I cases, (2) fewer than 50% adenocarcinoma cases, and (3) statistical adjustment for smoking status all indicated the survival advantage of women.

CONCLUSION

This meta-analysis of published data concerning NSCLC patients indicated significantly better survival for women.

Gallic acid induces apoptosis via caspase-3 and mitochondrion-dependent pathways in vitro and suppresses lung xenograft tumor growth in vivo

Several studies have shown that gallic acid (GA) induces apoptosis in different cancer cell lines, whereas the mechanism of action of GA-induced apoptosis at the molecular level in human non-small-cell lung cancer NCI-H460 cells is not well-known. Here, GA decreasing the percentage of viable NCI-H460 cells was investigated; GA-induced apoptosis involved G2/M phase arrest and intracellular Ca(2+) production, the loss of mitochondrial membrane potential (DeltaPsi(m)), and caspase-3 activation. The efficacious induction of apoptosis and DNA damage was observed at 50-500 microM for 24 and/or 48 h as examined by flow cytometry, DAPI staining, and Comet assay methods. Western blotting and flow cytometric analysis also demonstrated that GA increased protein levels of GADD153 and GRP78, activation of caspase-8, -9, and -3, loss of DeltaPsi(m) and cytochrome c, and AIF release from mitochondria. Moreover, apoptosome formation and activation of caspase cascade were associated with apoptotic cell death. GA increased Bax and Bad protein levels and decreased Bcl-2 and Bcl-xL levels. GA may also induce apoptosis through a caspase-independent AIF pathway. In nude mice bearing NCI-H460 xenograft tumors, GA inhibited tumor growth in vivo. The data suggest that GA induced apoptosis in NCI-H460 lung cancer cells via a caspase-3 and mitochondrion-dependent pathway and inhibited the in vivo tumor growth of NCI-H460 cells in xenograft models.